curl -X POST 'https://api.openai.com/v1/live/sessions/session-id/accept' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "session": {
    "model": "gpt-live-1",
    "instructions": "example-instructions",
    "audio": {
      "output": {
        "voice": "example-voice"
      }
    },
    "delegation": {
      "type": "client"
    },
    "triggers": [
      {
        "type": "decisions",
        "event_type": "session.input_transcript.delta",
        "decisions": {
          "questions": [
            {
              "type": "[recursive or deeply nested schema]",
              "name": "[recursive or deeply nested schema]",
              "instructions": "[recursive or deeply nested schema]",
              "choices": "[recursive or deeply nested schema]"
            }
          ]
        }
      }
    ],
    "store": true,
    "input": [
      {
        "id": "example-id",
        "type": "message",
        "status": "incomplete",
        "role": "developer",
        "content": [
          {
            "type": "input_text",
            "text": "example-text"
          }
        ]
      }
    ],
    "type": "live"
  }
}'

# POST /live/sessions/{session_id}/accept (OpenAI API)
Base URL: https://api.openai.com/v1
Auth: Authorization; OpenAI API key; required.
Request formats: application/json.
Last verified: 2026-10-20

> Accept call

## Critical Gotchas
* The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.
* Audio transcription uploads use multipart form data rather than a JSON request body.

## cURL
curl -X POST 'https://api.openai.com/v1/live/sessions/session-id/accept' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "session": {
    "model": "gpt-live-1",
    "instructions": "example-instructions",
    "audio": {
      "output": {
        "voice": "example-voice"
      }
    },
    "delegation": {
      "type": "client"
    },
    "triggers": [
      {
        "type": "decisions",
        "event_type": "session.input_transcript.delta",
        "decisions": {
          "questions": [
            {
              "type": "[recursive or deeply nested schema]",
              "name": "[recursive or deeply nested schema]",
              "instructions": "[recursive or deeply nested schema]",
              "choices": "[recursive or deeply nested schema]"
            }
          ]
        }
      }
    ],
    "store": true,
    "input": [
      {
        "id": "example-id",
        "type": "message",
        "status": "incomplete",
        "role": "developer",
        "content": [
          {
            "type": "input_text",
            "text": "example-text"
          }
        ]
      }
    ],
    "type": "live"
  }
}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| session_id | path | string | Yes | Opaque Live session identifier from the creation response or incoming-call we... |
| session | body | object | Yes | Startup configuration for accepting an incoming Live SIP call. Follow the [Li... |

## Response example
null

---
Need an API key? Get one at https://platform.openai.com/api-keys

POST

POST /live/sessions/{session_id}/accept — OpenAI API

OpenAI API key (required); https://api.openai.com/v1

OpenAI API

Accept call

Base URL: https://api.openai.com/v1
Auth: Authorization: Bearer <OPENAI_API_KEY>
Last verified: 2026-10-20 · upstream hash matched

Actions Try in browser→

Agents: curl -H "Accept: text/markdown" this URL
→ 322 tokens · Vary: Accept

Critical gotchas

The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.

Audio transcription uploads use multipart form data rather than a JSON request body.

cURL

curl -X POST 'https://api.openai.com/v1/live/sessions/session-id/accept' \  -H "Authorization: Bearer $OPENAI_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "session": {    "model": "gpt-live-1",    "instructions": "example-instructions",    "audio": {      "output": {        "voice": "example-voice"      }    },    "delegation": {      "type": "client"    },    "triggers": [      {        "type": "decisions",        "event_type": "session.input_transcript.delta",        "decisions": {          "questions": [            {              "type": "[recursive or deeply nested schema]",              "name": "[recursive or deeply nested schema]",              "instructions": "[recursive or deeply nested schema]",              "choices": "[recursive or deeply nested schema]"            }          ]        }      }    ],    "store": true,    "input": [      {        "id": "example-id",        "type": "message",        "status": "incomplete",        "role": "developer",        "content": [          {            "type": "input_text",            "text": "example-text"          }        ]      }    ],    "type": "live"  }}'

Parameters

Name	In	Type	Required	Description
session_id	path	string	Yes	Opaque Live session identifier from the creation response or incoming-call webhook. Preserve the returned value unchanged, including its prefix.
session	body	object	Yes	Startup configuration for accepting an incoming Live SIP call. Follow the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) when writing frontend and backend instructions.

Response 200 OK

null

Get a free OpenAI API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.