curl -X POST 'https://api.elevenlabs.io/v1/convai/conversations/conversation-id/analysis/evaluations/run' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "evaluation_id": "string",
  "scope": "conversation"
}'

# POST /v1/convai/conversations/{conversation_id}/analysis/evaluations/run (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03

> Run Conversation Evaluation

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/convai/conversations/conversation-id/analysis/evaluations/run' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"evaluation_id":"string","scope":"conversation"}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| conversation_id | path | string | Yes | ID of the conversation |
| evaluation_id | body | string | Yes | ID of the single evaluation criterion to rerun. |
| scope | body | string | No | Request body field scope. |

## Response (200 OK)
{"agent_id":"agent_3701k3ttaq12ewp8b7qv5rfyszkz","agent_name":"My agent"}

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

/v1/convai/conversations/{conversation_id}/analysis/evaluations/run

ElevenLabs API

Run Conversation Evaluation

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03 · upstream hash matched

Actions

Agents: curl -H "Accept: text/markdown" this URL
→ 210 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/convai/conversations/conversation-id/analysis/evaluations/run' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "evaluation_id": "string",  "scope": "conversation"}'

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
conversation_id	path	string	Yes	ID of the conversation
evaluation_id	body	string	Yes	ID of the single evaluation criterion to rerun.
scope	body	string	No	Request body field scope.

Response 200 OK

{
  "agent_id": "agent_3701k3ttaq12ewp8b7qv5rfyszkz",
  "agent_name": "My agent",
  "conversation_id": "conv_7401k5m9x2p8ec3rqv6dtnhb0fzw",
  "environment": "production",
  "has_audio": true,
  "has_auxiliary_audio": true,
  "has_response_audio": true,
  "has_user_audio": true,
  "metadata": {
    "call_duration_secs": 10,
    "start_time_unix_secs": 1714423232
  },
  "status": "processing",
  "tag_ids": [],
  "transcript": [
    {
      "message": "Hello, how are you?",
      "role": "user",
      "time_in_call_secs": 10
    }
  ],
  "version_id": "agtvrsn_5xM3yVvZQKV0EfqQpLr2"
}