Realtime

Accept call

Accept an incoming SIP call and configure the realtime session that will handle it.

post/realtime/calls/{call_id}/accept

Path parameters

call_idstring required

The identifier for the call provided in the realtime.call.incoming webhook.

Request body

type'realtime' required

The type of session to create. Always realtime for the Realtime API.

output_modalitiesstring[]

The set of modalities the model can respond with. It defaults to ["audio"], indicating that the model will respond with audio plus a transcript. ["text"] can be used to make the model respond with text only. It is not possible to request both text and audio at the same time.

instructionsstring

The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.

Note that the server sets default instructions which will be used if this field is not set and are visible in the session.created event at the start of the session.

includestring[]

Additional fields to include in server outputs.

item.input_audio_transcription.logprobs: Include logprobs for input audio transcription.

parallel_tool_callsboolean

Whether the model may call multiple tools in parallel. Only supported by reasoning Realtime models such as gpt-realtime-2.

Example request

{
  "audio": {
    "output": {
      "voice": {
        "id": "voice_1234"
      }
    }
  }
}

Response

Call accepted successfully.

Changes

Changed in 6 of the 31 revisions of this API.317

Jul 28, 2026c7549184dd954See the full diff
- ○
  added the new optional request property audio/input/transcription/keywords
  new-optional-request-property
- ○
  added the new optional request property audio/input/transcription/languages
  new-optional-request-property
- ○
  added the new gpt-live-transcribe enum value to the request property audio/input/transcription/model/anyOf[subschema #2]/
  request-property-enum-value-added
- ○
  added the new gpt-transcribe enum value to the request property audio/input/transcription/model/anyOf[subschema #2]/
  request-property-enum-value-added
This revision also has 1 change that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
Jul 9, 2026e0508a503b847See the full diff
- ○
  added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #2: Input text]/prompt_cache_breakpoint
  new-optional-request-property
- ○
  added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #3: Input image]/prompt_cache_breakpoint
  new-optional-request-property
- ○
  added the new optional request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #4: Input file]/prompt_cache_breakpoint
  new-optional-request-property
- ○
  added the new optional request property tools/items/anyOf[subschema #2: MCP tool]/allowed_callers
  new-optional-request-property
- ○
  added the new auto enum value to the request property prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #4: Input file]/detail
  request-property-enum-value-added
- ○
  added the new gpt-realtime-2.1 enum value to the request property model/anyOf[subschema #2]/
  request-property-enum-value-added
- ○
  added the new gpt-realtime-2.1-mini enum value to the request property model/anyOf[subschema #2]/
  request-property-enum-value-added
This revision also has 1 change that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog
Jun 17, 2026827fa3e74ce91See the full diff
- ○
  added the new optional request property tools/items/anyOf[subschema #2: MCP tool]/tunnel_id
  new-optional-request-property
May 7, 202681aa43d6a9f15See the full diff
- ○
  added the new optional request property audio/input/transcription/delay
  new-optional-request-property
- ○
  added the new optional request property parallel_tool_calls
  new-optional-request-property
- ○
  added the new optional request property reasoning
  new-optional-request-property
- ○
  added the new gpt-realtime-2 enum value to the request property model/anyOf[subschema #2]/
  request-property-enum-value-added
- ○
  added the new gpt-realtime-whisper enum value to the request property audio/input/transcription/model/anyOf[subschema #2]/
  request-property-enum-value-added
May 4, 202664494d56c4252See the full diff
- ▲
  the prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #3: Input image]/image_url/anyOf[subschema #1]/ request property type/format changed from string/ to string/uri
  request-property-type-changed
- ▲
  the prompt/anyOf[subschema #1]/variables/anyOf[subschema #1: Prompt Variables]/additionalProperties/anyOf[subschema #4: Input file]/file_url request property type/format changed from string/ to string/uri
  request-property-type-changed
Apr 29, 20265b98524f8dee1See the full diff
- ▲
  the tools/items/anyOf[subschema #2: MCP tool]/server_url request property type/format changed from string/ to string/uri
  request-property-type-changed

Full history