Voiceflow bearer token
Evaluations
Score the quality of conversations.
Paste in your agent
1. Set up Voiceflow by following https://www.voiceflow.com/agents/setup 2. Read https://www.voiceflow.com/docs/api-reference/resources/evaluation.md — the Voiceflow documentation page "Evaluations". Use it to help me with this part of Voiceflow and answer my questions. Refer to https://www.voiceflow.com/docs/llms.txt if you need related documentation.
See Authentication for credentials and permissions.
Current - 2026/07
/v1/stable/evaluationReturns every evaluation in the project. An evaluation is a criterion a model scores past conversations against. The call takes no paging parameters, so one request yields the whole set.
curl --request GET \
--url 'https://realtime-api.voiceflow.com/v1/stable/evaluation?projectID=<projectID>' \
--header 'Authorization: Bearer <token>'const response = await fetch('https://realtime-api.voiceflow.com/v1/stable/evaluation?projectID=<projectID>', {
method: 'GET',
headers: {
Authorization: 'Bearer <token>',
},
});
const data = await response.json();import requests
response = requests.get(
'https://realtime-api.voiceflow.com/v1/stable/evaluation?projectID=<projectID>',
headers={'Authorization': 'Bearer <token>'},
)
data = response.json()vf evaluation list --project-id <projectID>{
"evaluations": [
{
"id": "<string>",
"name": "<string>",
"prompt": "<string>",
"default": true,
"enabled": true,
"projectID": "<string>",
"settings": "<AgentSettings>",
"averageCost": 0,
"description": "<string>"
}
]
}Authentication
Query parameters
The ID of the project to operate on.
Response
200 - application/jsonReturns every evaluation defined on the project, each with the criteria it judges transcripts against, its result type, whether it runs automatically on new transcripts, and its average cost per run.
/v1/stable/evaluationAdds a evaluation to the project, a criterion a model scores past conversations against. The response carries the ID that later calls address it by.
curl --request POST \
--url 'https://realtime-api.voiceflow.com/v1/stable/evaluation?projectID=<projectID>' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"type": "boolean",
"truePrompt": "<string>",
"falsePrompt": "<string>",
"name": "<string>",
"prompt": "<string>",
"enabled": true,
"description": "<string>"
}'const response = await fetch('https://realtime-api.voiceflow.com/v1/stable/evaluation?projectID=<projectID>', {
method: 'POST',
headers: {
Authorization: 'Bearer <token>',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"type": "boolean",
"truePrompt": "<string>",
"falsePrompt": "<string>",
"name": "<string>",
"prompt": "<string>",
"enabled": true,
"description": "<string>"
}),
});
const data = await response.json();import requests
response = requests.post(
'https://realtime-api.voiceflow.com/v1/stable/evaluation?projectID=<projectID>',
headers={'Authorization': 'Bearer <token>'},
json={
"type": "boolean",
"truePrompt": "<string>",
"falsePrompt": "<string>",
"name": "<string>",
"prompt": "<string>",
"enabled": True,
"description": "<string>"
},
)
data = response.json()vf evaluation create --project-id <projectID> <<'JSON'
{
"type": "boolean",
"truePrompt": "<string>",
"falsePrompt": "<string>",
"name": "<string>",
"prompt": "<string>",
"enabled": true,
"description": "<string>"
}
JSON{
"evaluation": {
"id": "<string>",
"name": "<string>",
"prompt": "<string>",
"default": true,
"enabled": true,
"projectID": "<string>",
"settings": "<AgentSettings>",
"averageCost": 0,
"description": "<string>"
}
}Authentication
Voiceflow bearer token
Query parameters
The ID of the project to operate on.
Request body
Show child attributes
Show child attributes
Identifies an evaluation that produces a true/false result.
booleanThe criteria describing when the evaluator should return true.
The criteria describing when the evaluator should return false.
The criteria the evaluator uses to judge a transcript.
Whether this evaluation runs automatically against new transcripts.
A human-readable description of what this evaluation measures.
Show child attributes
Identifies an evaluation that produces a numeric score.
numberThe lowest score the evaluator can assign.
The highest score the evaluator can assign.
The criteria describing what warrants the minimumValue score.
The criteria describing what warrants the maximumValue score.
The criteria the evaluator uses to judge a transcript.
Whether this evaluation runs automatically against new transcripts.
A human-readable description of what this evaluation measures.
Show child attributes
Identifies an evaluation that produces a free-form text result.
stringThe criteria the evaluator uses to judge a transcript.
Whether this evaluation runs automatically against new transcripts.
A human-readable description of what this evaluation measures.
Show child attributes
Identifies an evaluation that selects one of a predefined set of options.
optionShow child attributes
The value assigned to the evaluation result when this option is selected.
The criteria describing when the evaluator should select this option.
Whether this option is available for the evaluator to select.
The color used to display this option in the Voiceflow UI.
The criteria the evaluator uses to judge a transcript.
Whether this evaluation runs automatically against new transcripts.
A human-readable description of what this evaluation measures.
Response
201 - application/jsonCreates the evaluation and returns it with its assigned id. No transcript is scored yet: results come from running it against a transcript, or automatically on new transcripts when enabled is true.
Legacy - 2026/11
/v2/stable/evaluationList all evaluations by project ID, without their judge prompts.
curl --request GET \
--url 'https://realtime-api.voiceflow.com/v2/stable/evaluation?projectID=<projectID>' \
--header 'Authorization: Bearer <token>'const response = await fetch('https://realtime-api.voiceflow.com/v2/stable/evaluation?projectID=<projectID>', {
method: 'GET',
headers: {
Authorization: 'Bearer <token>',
},
});
const data = await response.json();import requests
response = requests.get(
'https://realtime-api.voiceflow.com/v2/stable/evaluation?projectID=<projectID>',
headers={'Authorization': 'Bearer <token>'},
)
data = response.json()vf evaluation list --project-id <projectID>{
"evaluations": [
{
"id": "<string>",
"name": "<string>",
"type": "boolean",
"enabled": true,
"default": true,
"description": "<string>"
}
]
}Authentication
Voiceflow bearer token
Query parameters
The ID of the project to operate on.
Response
200 - application/jsonCurrent - 2026/07
/v1/stable/evaluation/{evaluationID}Returns a single evaluation by ID, with the fields that define it. An evaluation is a criterion a model scores past conversations against.
curl --request GET \
--url 'https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>' \
--header 'Authorization: Bearer <token>'const response = await fetch('https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>', {
method: 'GET',
headers: {
Authorization: 'Bearer <token>',
},
});
const data = await response.json();import requests
response = requests.get(
'https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>',
headers={'Authorization': 'Bearer <token>'},
)
data = response.json()vf evaluation get --evaluation-id <evaluationID> --project-id <projectID>{
"evaluation": {
"id": "<string>",
"name": "<string>",
"prompt": "<string>",
"default": true,
"enabled": true,
"projectID": "<string>",
"settings": "<AgentSettings>",
"averageCost": 0,
"description": "<string>"
}
}Authentication
Voiceflow bearer token
Path parameters
The ID of the evaluation to operate on.
Query parameters
The ID of the project to operate on.
Response
200 - application/jsonReturns one evaluation in full: the criteria prompts for its result type, the model settings the evaluator judges with, and whether it is one of the built-in defaults.
Current - 2026/07
/v1/stable/evaluation/{evaluationID}Changes an existing evaluation in place. The response carries only a confirmation message, so refetch the evaluation to read its new values.
curl --request PATCH \
--url 'https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"truePrompt": "<string>",
"falsePrompt": "<string>",
"name": "<string>",
"prompt": "<string>",
"enabled": true,
"settings": {
"model": "<AIModel>",
"realtime": {
"voice": "<string>",
"eagerness": "<string>"
},
"maxTokens": 0,
"temperature": 0,
"reasoningEffort": "<AIReasoningEffort>",
"serviceTier": "<AIParamsServiceTier>"
},
"description": "<string>",
"type": "boolean"
}'const response = await fetch('https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>', {
method: 'PATCH',
headers: {
Authorization: 'Bearer <token>',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"truePrompt": "<string>",
"falsePrompt": "<string>",
"name": "<string>",
"prompt": "<string>",
"enabled": true,
"settings": {
"model": "<AIModel>",
"realtime": {
"voice": "<string>",
"eagerness": "<string>"
},
"maxTokens": 0,
"temperature": 0,
"reasoningEffort": "<AIReasoningEffort>",
"serviceTier": "<AIParamsServiceTier>"
},
"description": "<string>",
"type": "boolean"
}),
});
const data = await response.json();import requests
response = requests.patch(
'https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>',
headers={'Authorization': 'Bearer <token>'},
json={
"truePrompt": "<string>",
"falsePrompt": "<string>",
"name": "<string>",
"prompt": "<string>",
"enabled": True,
"settings": {
"model": "<AIModel>",
"realtime": {
"voice": "<string>",
"eagerness": "<string>"
},
"maxTokens": 0,
"temperature": 0,
"reasoningEffort": "<AIReasoningEffort>",
"serviceTier": "<AIParamsServiceTier>"
},
"description": "<string>",
"type": "boolean"
},
)
data = response.json()vf evaluation update --evaluation-id <evaluationID> --project-id <projectID> <<'JSON'
{
"truePrompt": "<string>",
"falsePrompt": "<string>",
"name": "<string>",
"prompt": "<string>",
"enabled": true,
"settings": {
"model": "<AIModel>",
"realtime": {
"voice": "<string>",
"eagerness": "<string>"
},
"maxTokens": 0,
"temperature": 0,
"reasoningEffort": "<AIReasoningEffort>",
"serviceTier": "<AIParamsServiceTier>"
},
"description": "<string>",
"type": "boolean"
}
JSON{
"message": "<string>"
}Authentication
Voiceflow bearer token
Path parameters
The ID of the evaluation to operate on.
Query parameters
The ID of the project to operate on.
Request body
Show child attributes
Show child attributes
The criteria describing when the evaluator should return true.
The criteria describing when the evaluator should return false.
The criteria the evaluator uses to judge a transcript.
Whether this evaluation runs automatically against new transcripts.
Show child attributes
Show child attributes
The service tier to request from models that support it. priority is faster processing: faster responses at a higher credit cost. When unset, the deprecated project-level priorityProcessing setting applies.
A human-readable description of what this evaluation measures.
Identifies an evaluation that produces a true/false result.
booleanShow child attributes
The lowest score the evaluator can assign.
The highest score the evaluator can assign.
The criteria describing what warrants the minimumValue score.
The criteria describing what warrants the maximumValue score.
The criteria the evaluator uses to judge a transcript.
Whether this evaluation runs automatically against new transcripts.
Show child attributes
Show child attributes
The service tier to request from models that support it. priority is faster processing: faster responses at a higher credit cost. When unset, the deprecated project-level priorityProcessing setting applies.
A human-readable description of what this evaluation measures.
Identifies an evaluation that produces a numeric score.
numberShow child attributes
The criteria the evaluator uses to judge a transcript.
Whether this evaluation runs automatically against new transcripts.
Show child attributes
Show child attributes
The service tier to request from models that support it. priority is faster processing: faster responses at a higher credit cost. When unset, the deprecated project-level priorityProcessing setting applies.
A human-readable description of what this evaluation measures.
Identifies an evaluation that produces a free-form text result.
stringShow child attributes
Show child attributes
The value assigned to the evaluation result when this option is selected.
The criteria describing when the evaluator should select this option.
Whether this option is available for the evaluator to select.
The color used to display this option in the Voiceflow UI.
The criteria the evaluator uses to judge a transcript.
Whether this evaluation runs automatically against new transcripts.
Show child attributes
Show child attributes
The service tier to request from models that support it. priority is faster processing: faster responses at a higher credit cost. When unset, the deprecated project-level priorityProcessing setting applies.
A human-readable description of what this evaluation measures.
Identifies an evaluation that selects one of a predefined set of options.
optionResponse
200 - application/jsonConfirms the evaluation's name, criteria, result type, or enabled state were updated. The body is a message only, so refetch the evaluation to read its stored definition.
A human-readable message confirming the update.
Current - 2026/07
/v1/stable/evaluation/{evaluationID}Deletes a single evaluation by ID. An evaluation is a criterion a model scores past conversations against. The response carries only a confirmation message, so refetch the evaluations to see what is left.
curl --request DELETE \
--url 'https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>' \
--header 'Authorization: Bearer <token>'const response = await fetch('https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>', {
method: 'DELETE',
headers: {
Authorization: 'Bearer <token>',
},
});
const data = await response.json();import requests
response = requests.delete(
'https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>?projectID=<projectID>',
headers={'Authorization': 'Bearer <token>'},
)
data = response.json()vf evaluation delete --evaluation-id <evaluationID> --project-id <projectID>{
"message": "<string>"
}Authentication
Voiceflow bearer token
Path parameters
The ID of the evaluation to operate on.
Query parameters
The ID of the project to operate on.
Response
200 - application/jsonConfirms the evaluation was removed from the project. The body carries a message only, so drop any cached copy of the project's evaluations.
A human-readable message confirming the deletion.
Current - 2026/07
/v1/stable/evaluation/{evaluationID}/runScores one finished conversation against an evaluation. The response carries the verdict together with the reasoning behind it, so a low score says why.
curl --request POST \
--url 'https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>/run?projectID=<projectID>' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"transcriptID": "<string>"
}'const response = await fetch('https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>/run?projectID=<projectID>', {
method: 'POST',
headers: {
Authorization: 'Bearer <token>',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"transcriptID": "<string>"
}),
});
const data = await response.json();import requests
response = requests.post(
'https://realtime-api.voiceflow.com/v1/stable/evaluation/<evaluationID>/run?projectID=<projectID>',
headers={'Authorization': 'Bearer <token>'},
json={
"transcriptID": "<string>"
},
)
data = response.json()vf evaluation run --evaluation-id <evaluationID> --project-id <projectID> <<'JSON'
{
"transcriptID": "<string>"
}
JSON{
"result": {
"cost": 0,
"value": true,
"reason": "<string>",
"transcriptID": "<string>",
"evaluationID": "<string>"
}
}Authentication
Voiceflow bearer token
Path parameters
The ID of the evaluation to operate on.
Query parameters
The ID of the project to operate on.
Request body
The ID of the transcript to run the evaluation against.
Response
201 - application/jsonScores the transcript named in the body against this evaluation and returns the result: the value the evaluator produced, typed to match the evaluation, the reason behind it, and the LLM cost the run incurred.
/v1/stable/evaluation/queue-runsQueue evaluations against transcripts.
curl --request POST \
--url 'https://realtime-api.voiceflow.com/v1/stable/evaluation/queue-runs?projectID=<projectID>' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"evaluationIDs": [
"<string>"
],
"transcriptIDs": [
"<string>"
]
}'const response = await fetch('https://realtime-api.voiceflow.com/v1/stable/evaluation/queue-runs?projectID=<projectID>', {
method: 'POST',
headers: {
Authorization: 'Bearer <token>',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"evaluationIDs": [
"<string>"
],
"transcriptIDs": [
"<string>"
]
}),
});
const data = await response.json();import requests
response = requests.post(
'https://realtime-api.voiceflow.com/v1/stable/evaluation/queue-runs?projectID=<projectID>',
headers={'Authorization': 'Bearer <token>'},
json={
"evaluationIDs": [
"<string>"
],
"transcriptIDs": [
"<string>"
]
},
)
data = response.json()vf evaluation queue-runs --project-id <projectID> <<'JSON'
{
"evaluationIDs": [
"<string>"
],
"transcriptIDs": [
"<string>"
]
}
JSON{
"evaluationCount": 0,
"transcriptCount": 0,
"warning": {
"type": "quota_exceeded",
"message": "<string>",
"skippedTranscriptIDs": [
"<string>"
]
}
}Authentication
Voiceflow bearer token
Query parameters
The ID of the project to operate on.
Request body
The evaluations to run, 1 to 10. Every evaluation runs against every transcript.
The transcripts to score, 1 to 100.
Response
202 - application/jsonEvaluation runs queued across all transcripts.
Transcripts queued for at least one evaluation. Lower than the number sent when some were skipped: another project, not ended yet, or expired.
Set when the evaluation quota made the queue skip transcripts; it names them.
Show child attributes
quota_exceededLegacy - 2025/05
/v1/transcript-evaluation/project/{projectID}Get all project evaluations including the number of results per evaluation
curl --request GET \
--url 'https://analytics-api.voiceflow.com/v1/transcript-evaluation/project/<projectID>' \
--header 'Authorization: <api-key>'const response = await fetch('https://analytics-api.voiceflow.com/v1/transcript-evaluation/project/<projectID>', {
method: 'GET',
headers: {
Authorization: '<api-key>',
},
});
const data = await response.json();import requests
response = requests.get(
'https://analytics-api.voiceflow.com/v1/transcript-evaluation/project/<projectID>',
headers={'Authorization': '<api-key>'},
)
data = response.json(){
"evaluations": [
{
"id": "<string>",
"projectID": "<string>",
"name": "<string>",
"description": "<string>",
"default": true,
"enabled": true,
"averageCost": 0,
"prompt": "<string>",
"settings": "<Legacy4_TranscriptEvaluationSettings>",
"systemTag": "<string>",
"type": "boolean",
"truePrompt": "<string>",
"falsePrompt": "<string>"
}
]
}Authentication
Voiceflow API key
Path parameters
ID of the target Voiceflow project.
Response
200 - application/jsonLegacy - 2025/05
/v1/transcript-evaluation/{evaluationID}Get the definition of the specified transcript evaluation.
curl --request GET \
--url 'https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>' \
--header 'Authorization: <api-key>'const response = await fetch('https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>', {
method: 'GET',
headers: {
Authorization: '<api-key>',
},
});
const data = await response.json();import requests
response = requests.get(
'https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>',
headers={'Authorization': '<api-key>'},
)
data = response.json(){
"evaluation": {
"id": "<string>",
"projectID": "<string>",
"name": "<string>",
"description": "<string>",
"default": true,
"enabled": true,
"averageCost": 0,
"prompt": "<string>",
"settings": "<Legacy5_AgentSettings>",
"systemTag": "<string>",
"type": "boolean",
"truePrompt": "<string>",
"falsePrompt": "<string>"
}
}Authentication
Voiceflow API key
Path parameters
ID of the transcript evaluation to target.
Response
200 - application/jsonLegacy - 2025/05
/v1/transcript-evaluation/{evaluationID}Update the definition of the specified transcript evaluation.
curl --request PATCH \
--url 'https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>' \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"name": "<string>",
"description": "<string>",
"enabled": true,
"prompt": "<string>",
"settings": "<Legacy6_AgentSettings>",
"truePrompt": "<string>",
"falsePrompt": "<string>"
}'const response = await fetch('https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>', {
method: 'PATCH',
headers: {
Authorization: '<api-key>',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"name": "<string>",
"description": "<string>",
"enabled": true,
"prompt": "<string>",
"settings": "<Legacy6_AgentSettings>",
"truePrompt": "<string>",
"falsePrompt": "<string>"
}),
});
// This operation returns no response body.
console.log(response.status);import requests
response = requests.patch(
'https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>',
headers={'Authorization': '<api-key>'},
json={
"name": "<string>",
"description": "<string>",
"enabled": True,
"prompt": "<string>",
"settings": "<Legacy6_AgentSettings>",
"truePrompt": "<string>",
"falsePrompt": "<string>"
},
)
response.raise_for_status()
# This operation returns no response body.Authentication
Voiceflow API key
Path parameters
ID of the transcript evaluation to target.
Request body
Show child attributes
Show child attributes
Name of the evaluation.
Description of the evaluation.
When enabled, evaluations will be run on every new transcript.
This prompt describes how the LLM should apply this evaluation.
The model settings passed when invoking this evaluation.
Show child attributes
Show child attributes
This prompt describes which transcripts should evaluate as 'true'.
This prompt describes which transcripts should evaluate as 'false'.
Show child attributes
Name of the evaluation.
Description of the evaluation.
When enabled, evaluations will be run on every new transcript.
This prompt describes how the LLM should apply this evaluation.
The model settings passed when invoking this evaluation.
Show child attributes
Show child attributes
This prompt describes which transcripts should receive lower ratings.
This prompt describes which transcripts should receive higher ratings.
Show child attributes
Name of the evaluation.
Description of the evaluation.
When enabled, evaluations will be run on every new transcript.
This prompt describes how the LLM should apply this evaluation.
The model settings passed when invoking this evaluation.
Show child attributes
Show child attributes
Show child attributes
Name of the evaluation.
Description of the evaluation.
When enabled, evaluations will be run on every new transcript.
This prompt describes how the LLM should apply this evaluation.
The model settings passed when invoking this evaluation.
Show child attributes
Show child attributes
The options that should be evaluated for.
Response
204Legacy - 2025/05
/v1/transcript-evaluation/{evaluationID}Remove the specified evaluation along with results for all transcripts.
curl --request DELETE \
--url 'https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>' \
--header 'Authorization: <api-key>'const response = await fetch('https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>', {
method: 'DELETE',
headers: {
Authorization: '<api-key>',
},
});
// This operation returns no response body.
console.log(response.status);import requests
response = requests.delete(
'https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>',
headers={'Authorization': '<api-key>'},
)
response.raise_for_status()
# This operation returns no response body.Authentication
Voiceflow API key
Path parameters
ID of the transcript evaluation to target.
Response
204Legacy - 2025/05
/v1/transcript-evaluation/{evaluationID}/transcript/{transcriptID}Run a single evaluation for the specified transcript.
curl --request POST \
--url 'https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>/transcript/<transcriptID>' \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"projectID": "<string>"
}'const response = await fetch('https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>/transcript/<transcriptID>', {
method: 'POST',
headers: {
Authorization: '<api-key>',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"projectID": "<string>"
}),
});
const data = await response.json();import requests
response = requests.post(
'https://analytics-api.voiceflow.com/v1/transcript-evaluation/<evaluationID>/transcript/<transcriptID>',
headers={'Authorization': '<api-key>'},
json={
"projectID": "<string>"
},
)
data = response.json(){
"result": {
"transcriptID": "<string>",
"evaluationID": "<string>",
"value": 0,
"reason": "<string>",
"cost": 0
}
}Authentication
Voiceflow API key
Path parameters
ID of the transcript evaluation to target.
ID of the transcript to target.
Request body
Response
201 - application/jsonShow child attributes
Show child attributes
Schemas
AIModel
{"type":"string","enum":["gpt-3.5-turbo-1106","gpt-3.5-turbo","gpt-4","gpt-4o","gpt-4o-mini","gpt-4.1-2025-04-14","gpt-4.1-mini-2025-04-14","gpt-4.1-nano-2025-04-14","gpt-o3-mini","o3-2025-04-16","o4-mini-2025-04-16","gpt-5","gpt-5-mini","gpt-5-nano","gpt-5.2","gpt-5.4","gpt-5.4-mini","gpt-5.5","gpt-5.6-sol","gpt-5.6-terra","gpt-5.6-luna","gpt-6-sol","gpt-6-luna","gpt-6.1-sol","gpt-realtime","gpt-live-1","claude-4-opus","claude-4-sonnet","claude-4.5-sonnet","claude-4.6-sonnet","claude-4.5-haiku","claude-4.5-opus","claude-4.7-opus","bedrock-claude-4-sonnet","bedrock-claude-4.5-sonnet","bedrock-claude-4.6-sonnet","bedrock-claude-5-sonnet","bedrock-claude-5.5-sonnet","bedrock-claude-4.5-haiku","bedrock-claude-5.5-haiku","bedrock-claude-4.5-opus","bedrock-claude-4.7-opus","bedrock-claude-4.8-opus","voiceflow-core-4.0","voiceflow-core-4.1","voiceflow-core-4.2","voiceflow-flash-4.2","gemini-2.5-pro","gemini-2.5-flash","gemini-live-2.5-flash","gemini-3-flash","gemini-3.5-flash","gemini-3.1-pro","gpt-oss-20b","gpt-oss-120b","llama-guard-4","llama-3.1-instant","llama-3.3-versatile","qwen3.6-27b","grok-4.6","voiceflow-flash-4.1","kimi-k3","gemini-flash-2","gpt-4-turbo","claude-3.5-haiku","claude-3-opus","claude-3.7-sonnet","claude-v2","llama-3.2-1b-preview","gemini-pro-1.5","claude-3-haiku","claude-3-sonnet","text-davinci-003","claude-v1","claude-instant-v1","deep-seek-r1-distill-llama-70B","claude-3.5-sonnet"],"x-enumNames":["GPT_3_5_TURBO_1106","GPT_3_5_TURBO","GPT_4","GPT_4_O","GPT_4_O_MINI","GPT_4_1","GPT_4_1_MINI","GPT_4_1_NANO","GPT_O_3_MINI","GPT_O_3","GPT_O_4_MINI","GPT_5","GPT_5_MINI","GPT_5_NANO","GPT_5_2","GPT_5_4","GPT_5_4_MINI","GPT_5_5","GPT_5_6_SOL","GPT_5_6_TERRA","GPT_5_6_LUNA","GPT_6_SOL","GPT_6_LUNA","GPT_6_1_SOL","GPT_REALTIME","GPT_LIVE_1","CLAUDE_4_OPUS","CLAUDE_4_SONNET","CLAUDE_4_5_SONNET","CLAUDE_4_6_SONNET","CLAUDE_4_5_HAIKU","CLAUDE_4_5_OPUS","CLAUDE_4_7_OPUS","BEDROCK_CLAUDE_4_SONNET","BEDROCK_CLAUDE_4_5_SONNET","BEDROCK_CLAUDE_4_6_SONNET","BEDROCK_CLAUDE_5_SONNET","BEDROCK_CLAUDE_5_5_SONNET","BEDROCK_CLAUDE_4_5_HAIKU","BEDROCK_CLAUDE_5_5_HAIKU","BEDROCK_CLAUDE_4_5_OPUS","BEDROCK_CLAUDE_4_7_OPUS","BEDROCK_CLAUDE_4_8_OPUS","VOICEFLOW_CORE_4_0","VOICEFLOW_CORE_4_1","VOICEFLOW_CORE_4_2","VOICEFLOW_FLASH_4_2","GEMINI_2_5_PRO","GEMINI_2_5_FLASH","GEMINI_LIVE_2_5_FLASH","GEMINI_3_FLASH","GEMINI_3_5_FLASH","GEMINI_3_1_PRO","GPT_OSS_20_B","GPT_OSS_120_B","LLAMA_GUARD_4","LLAMA_3_1_INSTANT","LLAMA_3_3_VERSATILE","QWEN_3_6_27_B","GROK_4_6","VOICEFLOW_FLASH_4_1","KIMI_K_3","GEMINI_FLASH_2","GPT_4_TURBO","CLAUDE_3_5_HAIKU","CLAUDE_3_OPUS","CLAUDE_3_7_SONNET","CLAUDE_V_2","LLAMA_3_2_1_B_PREVIEW","GEMINI_PRO_1_5","CLAUDE_3_HAIKU","CLAUDE_3_SONNET","DA_VINCI_003","CLAUDE_V_1","CLAUDE_INSTANT_V_1","DEEP_SEEK_R_1_DISTILL_LLAMA_70_B","CLAUDE_3_5_SONNET"]}
AIParamsServiceTier
{"type":"string","enum":["default","flex","priority"],"x-enumNames":["DEFAULT","FLEX","PRIORITY"]}
AIReasoningEffort
{"type":"string","enum":["off","adaptive","minimal","low","medium","high"],"x-enumNames":["OFF","ADAPTIVE","MINIMAL","LOW","MEDIUM","HIGH"]}
AgentSettings
{"type":"object"}
| Property | Definition |
|---|---|
model | {"allOf":[{"$ref":"AIModel"}]} |
realtime | {"type":"object","properties":{"voice":{"type":"string"},"eagerness":{"type":"string"}}} |
maxTokens | {"type":"number"} |
temperature | {"type":"number"} |
reasoningEffort | {"nullable":true,"allOf":[{"$ref":"AIReasoningEffort"}]} |
serviceTier | The service tier to request from models that support it. {"nullable":true,"allOf":[{"$ref":"AIParamsServiceTier"}]} |
Legacy4_AIModel / Legacy5_AIModel / Legacy6_AIModel
{"type":"string","enum":["gpt-3.5-turbo-1106","gpt-3.5-turbo","gpt-4","gpt-4o","gpt-4o-mini","gpt-4.1-2025-04-14","gpt-4.1-mini-2025-04-14","gpt-4.1-nano-2025-04-14","gpt-o3-mini","o3-2025-04-16","o4-mini-2025-04-16","gpt-5","gpt-5-mini","gpt-5-nano","gpt-5.2","gpt-5.4","gpt-5.4-mini","gpt-5.5","gpt-realtime","claude-4-opus","claude-4-sonnet","claude-4.5-sonnet","claude-4.6-sonnet","claude-4.5-haiku","claude-4.5-opus","claude-4.7-opus","bedrock-claude-4-sonnet","bedrock-claude-4.5-sonnet","bedrock-claude-4.6-sonnet","bedrock-claude-5-sonnet","bedrock-claude-4.5-haiku","bedrock-claude-4.5-opus","bedrock-claude-4.7-opus","bedrock-claude-4.8-opus","voiceflow-core-4.0","voiceflow-core-4.1","voiceflow-flash-4.1","gemini-2.5-pro","gemini-2.5-flash","gemini-live-2.5-flash","gemini-3-flash","gemini-3.5-flash","gemini-3.1-pro","gpt-oss-20b","gpt-oss-120b","llama-guard-4","llama-3.1-instant","llama-3.3-versatile","qwen3.6-27b","gemini-flash-2","gpt-4-turbo","claude-3.5-haiku","claude-3-opus","claude-3.7-sonnet","claude-v2","llama-3.2-1b-preview","gemini-pro-1.5","claude-3-haiku","claude-3-sonnet","text-davinci-003","claude-v1","claude-instant-v1","deep-seek-r1-distill-llama-70B","claude-3.5-sonnet"],"x-enumNames":["GPT_3_5_TURBO_1106","GPT_3_5_TURBO","GPT_4","GPT_4_O","GPT_4_O_MINI","GPT_4_1","GPT_4_1_MINI","GPT_4_1_NANO","GPT_O_3_MINI","GPT_O_3","GPT_O_4_MINI","GPT_5","GPT_5_MINI","GPT_5_NANO","GPT_5_2","GPT_5_4","GPT_5_4_MINI","GPT_5_5","GPT_REALTIME","CLAUDE_4_OPUS","CLAUDE_4_SONNET","CLAUDE_4_5_SONNET","CLAUDE_4_6_SONNET","CLAUDE_4_5_HAIKU","CLAUDE_4_5_OPUS","CLAUDE_4_7_OPUS","BEDROCK_CLAUDE_4_SONNET","BEDROCK_CLAUDE_4_5_SONNET","BEDROCK_CLAUDE_4_6_SONNET","BEDROCK_CLAUDE_5_SONNET","BEDROCK_CLAUDE_4_5_HAIKU","BEDROCK_CLAUDE_4_5_OPUS","BEDROCK_CLAUDE_4_7_OPUS","BEDROCK_CLAUDE_4_8_OPUS","VOICEFLOW_CORE_4_0","VOICEFLOW_CORE_4_1","VOICEFLOW_FLASH_4_1","GEMINI_2_5_PRO","GEMINI_2_5_FLASH","GEMINI_LIVE_2_5_FLASH","GEMINI_3_FLASH","GEMINI_3_5_FLASH","GEMINI_3_1_PRO","GPT_OSS_20_B","GPT_OSS_120_B","LLAMA_GUARD_4","LLAMA_3_1_INSTANT","LLAMA_3_3_VERSATILE","QWEN_3_6_27_B","GEMINI_FLASH_2","GPT_4_TURBO","CLAUDE_3_5_HAIKU","CLAUDE_3_OPUS","CLAUDE_3_7_SONNET","CLAUDE_V_2","LLAMA_3_2_1_B_PREVIEW","GEMINI_PRO_1_5","CLAUDE_3_HAIKU","CLAUDE_3_SONNET","DA_VINCI_003","CLAUDE_V_1","CLAUDE_INSTANT_V_1","DEEP_SEEK_R_1_DISTILL_LLAMA_70_B","CLAUDE_3_5_SONNET"]}
Legacy4_AIReasoningEffort / Legacy5_AIReasoningEffort / Legacy6_AIReasoningEffort
{"type":"string","enum":["minimal","low","medium","high"],"x-enumNames":["MINIMAL","LOW","MEDIUM","HIGH"]}
Legacy4_AgentSettings
{"type":"object"}
| Property | Definition |
|---|---|
model | {"allOf":[{"$ref":"Legacy4_AIModel"}]} |
realtime | {"type":"object","properties":{"voice":{"type":"string"},"eagerness":{"type":"string"}}} |
maxTokens | {"type":"number"} |
temperature | {"type":"number"} |
reasoningEffort | {"nullable":true,"allOf":[{"$ref":"Legacy4_AIReasoningEffort"}]} |
Legacy4_BooleanTranscriptEvaluation
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
projectID · required | {"type":"string"} |
name · required | {"type":"string"} |
description · required | {"nullable":true,"type":"string"} |
default · required | {"type":"boolean"} |
enabled · required | {"type":"boolean"} |
averageCost · required | {"nullable":true,"type":"number"} |
prompt · required | {"type":"string"} |
settings · required | {"$ref":"Legacy4_TranscriptEvaluationSettings"} |
systemTag · required | {"nullable":true,"type":"string"} |
type · required | {"type":"string","enum":["boolean"],"x-enumNames":["BOOLEAN"]} |
truePrompt · required | {"type":"string"} |
falsePrompt · required | {"type":"string"} |
Legacy4_NumberTranscriptEvaluation
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
projectID · required | {"type":"string"} |
name · required | {"type":"string"} |
description · required | {"nullable":true,"type":"string"} |
default · required | {"type":"boolean"} |
enabled · required | {"type":"boolean"} |
averageCost · required | {"nullable":true,"type":"number"} |
prompt · required | {"type":"string"} |
settings · required | {"$ref":"Legacy4_TranscriptEvaluationSettings"} |
systemTag · required | {"nullable":true,"type":"string"} |
type · required | {"type":"string","enum":["number"],"x-enumNames":["NUMBER"]} |
minimumValue · required | {"type":"number"} |
minimumPrompt · required | {"type":"string"} |
maximumValue · required | {"type":"number"} |
maximumPrompt · required | {"type":"string"} |
Legacy4_OptionTranscriptEvaluation
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
projectID · required | {"type":"string"} |
name · required | {"type":"string"} |
description · required | {"nullable":true,"type":"string"} |
default · required | {"type":"boolean"} |
enabled · required | {"type":"boolean"} |
averageCost · required | {"nullable":true,"type":"number"} |
prompt · required | {"type":"string"} |
settings · required | {"$ref":"Legacy4_TranscriptEvaluationSettings"} |
systemTag · required | {"nullable":true,"type":"string"} |
type · required | {"type":"string","enum":["option"],"x-enumNames":["OPTION"]} |
options · required | {"type":"array","items":{"$ref":"Legacy4_TranscriptEvaluationOptionSchema"}} |
Legacy4_StringTranscriptEvaluation
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
projectID · required | {"type":"string"} |
name · required | {"type":"string"} |
description · required | {"nullable":true,"type":"string"} |
default · required | {"type":"boolean"} |
enabled · required | {"type":"boolean"} |
averageCost · required | {"nullable":true,"type":"number"} |
prompt · required | {"type":"string"} |
settings · required | {"$ref":"Legacy4_TranscriptEvaluationSettings"} |
systemTag · required | {"nullable":true,"type":"string"} |
type · required | {"type":"string","enum":["string"],"x-enumNames":["STRING"]} |
Legacy4_TranscriptEvaluationOptionSchema / Legacy5_TranscriptEvaluationOptionSchema / Legacy6_TranscriptEvaluationOptionSchema
{"type":"object","additionalProperties":false}
| Property | Definition |
|---|---|
value · required | {"type":"string","minLength":1,"maxLength":100} |
prompt · required | {"type":"string","minLength":1,"maxLength":10000} |
included · required | {"type":"boolean"} |
color · required | {"type":"string"} |
Legacy4_TranscriptEvaluationResponse
{"oneOf":[{"$ref":"Legacy4_BooleanTranscriptEvaluation"},{"$ref":"Legacy4_NumberTranscriptEvaluation"},{"$ref":"Legacy4_StringTranscriptEvaluation"},{"$ref":"Legacy4_OptionTranscriptEvaluation"}]}
Legacy4_TranscriptEvaluationSettings
{"nullable":true,"allOf":[{"$ref":"Legacy4_AgentSettings"}]}
Legacy5_AgentSettings
{"type":"object"}
| Property | Definition |
|---|---|
model | {"allOf":[{"$ref":"Legacy5_AIModel"}]} |
realtime | {"type":"object","properties":{"voice":{"type":"string"},"eagerness":{"type":"string"}}} |
maxTokens | {"type":"number"} |
temperature | {"type":"number"} |
reasoningEffort | {"nullable":true,"allOf":[{"$ref":"Legacy5_AIReasoningEffort"}]} |
Legacy5_BooleanTranscriptEvaluation
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
projectID · required | {"type":"string"} |
name · required | {"type":"string"} |
description · required | {"nullable":true,"type":"string"} |
default · required | {"type":"boolean"} |
enabled · required | {"type":"boolean"} |
averageCost · required | {"nullable":true,"type":"number"} |
prompt · required | {"type":"string"} |
settings · required | {"$ref":"Legacy5_TranscriptEvaluationSettings"} |
systemTag · required | {"nullable":true,"type":"string"} |
type · required | {"type":"string","enum":["boolean"],"x-enumNames":["BOOLEAN"]} |
truePrompt · required | {"type":"string"} |
falsePrompt · required | {"type":"string"} |
Legacy5_NumberTranscriptEvaluation
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
projectID · required | {"type":"string"} |
name · required | {"type":"string"} |
description · required | {"nullable":true,"type":"string"} |
default · required | {"type":"boolean"} |
enabled · required | {"type":"boolean"} |
averageCost · required | {"nullable":true,"type":"number"} |
prompt · required | {"type":"string"} |
settings · required | {"$ref":"Legacy5_TranscriptEvaluationSettings"} |
systemTag · required | {"nullable":true,"type":"string"} |
type · required | {"type":"string","enum":["number"],"x-enumNames":["NUMBER"]} |
minimumValue · required | {"type":"number"} |
minimumPrompt · required | {"type":"string"} |
maximumValue · required | {"type":"number"} |
maximumPrompt · required | {"type":"string"} |
Legacy5_OptionTranscriptEvaluation
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
projectID · required | {"type":"string"} |
name · required | {"type":"string"} |
description · required | {"nullable":true,"type":"string"} |
default · required | {"type":"boolean"} |
enabled · required | {"type":"boolean"} |
averageCost · required | {"nullable":true,"type":"number"} |
prompt · required | {"type":"string"} |
settings · required | {"$ref":"Legacy5_TranscriptEvaluationSettings"} |
systemTag · required | {"nullable":true,"type":"string"} |
type · required | {"type":"string","enum":["option"],"x-enumNames":["OPTION"]} |
options · required | {"type":"array","items":{"$ref":"Legacy5_TranscriptEvaluationOptionSchema"}} |
Legacy5_StringTranscriptEvaluation
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
projectID · required | {"type":"string"} |
name · required | {"type":"string"} |
description · required | {"nullable":true,"type":"string"} |
default · required | {"type":"boolean"} |
enabled · required | {"type":"boolean"} |
averageCost · required | {"nullable":true,"type":"number"} |
prompt · required | {"type":"string"} |
settings · required | {"$ref":"Legacy5_TranscriptEvaluationSettings"} |
systemTag · required | {"nullable":true,"type":"string"} |
type · required | {"type":"string","enum":["string"],"x-enumNames":["STRING"]} |
Legacy5_TranscriptEvaluationResponse
{"oneOf":[{"$ref":"Legacy5_BooleanTranscriptEvaluation"},{"$ref":"Legacy5_NumberTranscriptEvaluation"},{"$ref":"Legacy5_StringTranscriptEvaluation"},{"$ref":"Legacy5_OptionTranscriptEvaluation"}]}
Legacy5_TranscriptEvaluationSettings
{"nullable":true,"allOf":[{"$ref":"Legacy5_AgentSettings"}]}
Legacy6_AgentSettings
{"type":"object"}
| Property | Definition |
|---|---|
model | {"allOf":[{"$ref":"Legacy6_AIModel"}]} |
realtime | {"type":"object","properties":{"voice":{"type":"string"},"eagerness":{"type":"string"}}} |
maxTokens | {"type":"number"} |
temperature | {"type":"number"} |
reasoningEffort | {"nullable":true,"allOf":[{"$ref":"Legacy6_AIReasoningEffort"}]} |
Legacy6_TranscriptEvaluationSettings
{"nullable":true,"allOf":[{"$ref":"Legacy6_AgentSettings"}]}
StableDeleteResponse
{"type":"object"}
| Property | Definition |
|---|---|
message · required | A human-readable message confirming the deletion. {"type":"string"} |
StableEvaluation
{"allOf":[{"type":"object","properties":{"id":{"type":"string"},"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"default":{"type":"boolean","description":"Whether this is a built-in default evaluation."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"projectID":{"type":"string","description":"The ID of the project this evaluation belongs to."},"settings":{"nullable":true,"allOf":[{"$ref":"AgentSettings"}]},"averageCost":{"nullable":true,"description":"The average LLM cost incurred each time this evaluation runs.","type":"number"},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"}},"required":["id","name","prompt","default","enabled","projectID","settings","averageCost","description"]},{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["boolean"],"description":"Identifies an evaluation that produces a true/false result.","x-enumNames":["BOOLEAN"]},"truePrompt":{"type":"string","description":"The criteria describing when the evaluator should return `true`."},"falsePrompt":{"type":"string","description":"The criteria describing when the evaluator should return `false`."}},"required":["type","truePrompt","falsePrompt"]},{"type":"object","properties":{"type":{"type":"string","enum":["number"],"description":"Identifies an evaluation that produces a numeric score.","x-enumNames":["NUMBER"]},"minimumValue":{"type":"number","description":"The lowest score the evaluator can assign."},"maximumValue":{"type":"number","description":"The highest score the evaluator can assign."},"minimumPrompt":{"type":"string","description":"The criteria describing what warrants the `minimumValue` score."},"maximumPrompt":{"type":"string","description":"The criteria describing what warrants the `maximumValue` score."}},"required":["type","minimumValue","maximumValue","minimumPrompt","maximumPrompt"]},{"type":"object","properties":{"type":{"type":"string","enum":["string"],"description":"Identifies an evaluation that produces a free-form text result.","x-enumNames":["STRING"]}},"required":["type"]},{"type":"object","properties":{"type":{"type":"string","enum":["option"],"description":"Identifies an evaluation that selects one of a predefined set of options.","x-enumNames":["OPTION"]},"options":{"type":"array","items":{"type":"object","properties":{"value":{"type":"string","description":"The value assigned to the evaluation result when this option is selected."},"prompt":{"type":"string","description":"The criteria describing when the evaluator should select this option."},"included":{"type":"boolean","description":"Whether this option is available for the evaluator to select."},"color":{"type":"string","description":"The color used to display this option in the Voiceflow UI."}},"required":["value","prompt","included","color"]}}},"required":["type","options"]}]}]}
StableEvaluationCreateRequest
{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["boolean"],"description":"Identifies an evaluation that produces a true/false result.","x-enumNames":["BOOLEAN"]},"truePrompt":{"type":"string","description":"The criteria describing when the evaluator should return `true`."},"falsePrompt":{"type":"string","description":"The criteria describing when the evaluator should return `false`."},"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"}},"required":["type","truePrompt","falsePrompt","name","prompt","enabled"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["number"],"description":"Identifies an evaluation that produces a numeric score.","x-enumNames":["NUMBER"]},"minimumValue":{"type":"number","description":"The lowest score the evaluator can assign."},"maximumValue":{"type":"number","description":"The highest score the evaluator can assign."},"minimumPrompt":{"type":"string","description":"The criteria describing what warrants the `minimumValue` score."},"maximumPrompt":{"type":"string","description":"The criteria describing what warrants the `maximumValue` score."},"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"}},"required":["type","minimumValue","maximumValue","minimumPrompt","maximumPrompt","name","prompt","enabled"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["string"],"description":"Identifies an evaluation that produces a free-form text result.","x-enumNames":["STRING"]},"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"}},"required":["type","name","prompt","enabled"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["option"],"description":"Identifies an evaluation that selects one of a predefined set of options.","x-enumNames":["OPTION"]},"options":{"type":"array","items":{"type":"object","properties":{"value":{"type":"string","description":"The value assigned to the evaluation result when this option is selected."},"prompt":{"type":"string","description":"The criteria describing when the evaluator should select this option."},"included":{"type":"boolean","description":"Whether this option is available for the evaluator to select."},"color":{"type":"string","description":"The color used to display this option in the Voiceflow UI."}},"required":["value","prompt","included","color"]}},"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"}},"required":["type","options","name","prompt","enabled"],"additionalProperties":false}]}
StableEvaluationListResponse
{"type":"object"}
| Property | Definition |
|---|---|
evaluations · required | {"type":"array","items":{"$ref":"StableEvaluation"}} |
StableEvaluationListResponseV2
{"type":"object"}
| Property | Definition |
|---|---|
evaluations · required | {"type":"array","items":{"$ref":"StableEvaluationSummary"}} |
StableEvaluationQueueRunsRequest
{"type":"object","additionalProperties":false}
| Property | Definition |
|---|---|
evaluationIDs · required | The evaluations to run, 1 to 10. Every evaluation runs against every transcript. {"minItems":1,"maxItems":10,"type":"array","items":{"type":"string"}} |
transcriptIDs · required | The transcripts to score, 1 to 100. {"minItems":1,"maxItems":100,"type":"array","items":{"type":"string"}} |
StableEvaluationQueueRunsResponse
{"type":"object"}
| Property | Definition |
|---|---|
evaluationCount · required | Evaluation runs queued across all transcripts. {"type":"integer","minimum":-9007199254740991,"maximum":9007199254740991} |
transcriptCount · required | Transcripts queued for at least one evaluation. Lower than the number sent when some were skipped: another project, not ended yet, or expired. {"type":"integer","minimum":-9007199254740991,"maximum":9007199254740991} |
warning | Set when the evaluation quota made the queue skip transcripts; it names them. {"type":"object","properties":{"type":{"type":"string","enum":["quota_exceeded"],"x-enumNames":["QUOTA_EXCEEDED"]},"message":{"type":"string"},"skippedTranscriptIDs":{"type":"array","items":{"type":"string"}}},"required":["type","message","skippedTranscriptIDs"]} |
StableEvaluationResponse
{"type":"object"}
| Property | Definition |
|---|---|
evaluation · required | {"$ref":"StableEvaluation"} |
StableEvaluationResult
{"type":"object"}
| Property | Definition |
|---|---|
cost · required | The LLM cost incurred by this evaluation run. {"type":"number"} |
value · required | The result produced by the evaluator; its type matches the evaluation {"anyOf":[{"type":"boolean"},{"type":"number"},{"type":"string"}]} |
reason · required | The evaluator's explanation for the returned {"type":"string"} |
transcriptID · required | The ID of the transcript that was evaluated. {"type":"string"} |
evaluationID · required | The ID of the evaluation that was run. {"type":"string"} |
StableEvaluationRunRequest
{"type":"object","additionalProperties":false}
| Property | Definition |
|---|---|
transcriptID · required | The ID of the transcript to run the evaluation against. {"type":"string"} |
StableEvaluationRunResponse
{"type":"object"}
| Property | Definition |
|---|---|
result · required | {"$ref":"StableEvaluationResult"} |
StableEvaluationSummary
{"type":"object"}
| Property | Definition |
|---|---|
id · required | {"type":"string"} |
name · required | {"type":"string"} |
type · required | {"type":"string","enum":["boolean","number","string","option"],"x-enumNames":["BOOLEAN","NUMBER","STRING","OPTION"]} |
enabled · required | Whether this evaluation runs automatically against new transcripts. {"type":"boolean"} |
default · required | Whether this is a built-in default evaluation. {"type":"boolean"} |
description · required | A human-readable description of what this evaluation measures. {"nullable":true,"type":"string"} |
StableEvaluationUpdateRequest
{"oneOf":[{"type":"object","properties":{"truePrompt":{"type":"string","description":"The criteria describing when the evaluator should return `true`."},"falsePrompt":{"type":"string","description":"The criteria describing when the evaluator should return `false`."},"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"settings":{"nullable":true,"allOf":[{"$ref":"AgentSettings"}]},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"},"type":{"type":"string","enum":["boolean"],"description":"Identifies an evaluation that produces a true/false result.","x-enumNames":["BOOLEAN"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"minimumValue":{"type":"number","description":"The lowest score the evaluator can assign."},"maximumValue":{"type":"number","description":"The highest score the evaluator can assign."},"minimumPrompt":{"type":"string","description":"The criteria describing what warrants the `minimumValue` score."},"maximumPrompt":{"type":"string","description":"The criteria describing what warrants the `maximumValue` score."},"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"settings":{"nullable":true,"allOf":[{"$ref":"AgentSettings"}]},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"},"type":{"type":"string","enum":["number"],"description":"Identifies an evaluation that produces a numeric score.","x-enumNames":["NUMBER"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"settings":{"nullable":true,"allOf":[{"$ref":"AgentSettings"}]},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"},"type":{"type":"string","enum":["string"],"description":"Identifies an evaluation that produces a free-form text result.","x-enumNames":["STRING"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"options":{"type":"array","items":{"type":"object","properties":{"value":{"type":"string","description":"The value assigned to the evaluation result when this option is selected."},"prompt":{"type":"string","description":"The criteria describing when the evaluator should select this option."},"included":{"type":"boolean","description":"Whether this option is available for the evaluator to select."},"color":{"type":"string","description":"The color used to display this option in the Voiceflow UI."}},"required":["value","prompt","included","color"]}},"name":{"type":"string"},"prompt":{"type":"string","description":"The criteria the evaluator uses to judge a transcript."},"enabled":{"type":"boolean","description":"Whether this evaluation runs automatically against new transcripts."},"settings":{"nullable":true,"allOf":[{"$ref":"AgentSettings"}]},"description":{"nullable":true,"description":"A human-readable description of what this evaluation measures.","type":"string"},"type":{"type":"string","enum":["option"],"description":"Identifies an evaluation that selects one of a predefined set of options.","x-enumNames":["OPTION"]}},"required":["type"],"additionalProperties":false}]}
StableUpdateResponse
{"type":"object"}
| Property | Definition |
|---|---|
message · required | A human-readable message confirming the update. {"type":"string"} |
Was this page helpful?
Thanks for your feedback.