curl -X POST 'https://api.openai.com/v1/realtime/calls/call-id/accept' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "type": "realtime"
}'

# POST /realtime/calls/{call_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/realtime/calls/call-id/accept' \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "type": "realtime"
}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| call_id | path | string | Yes | The identifier for the call provided in the [`realtime.call.incoming`](https:... |
| type | body | string | Yes | The type of session to create. Always `realtime` for the Realtime API.  |
| output_modalities | body | string[] | No | The set of modalities the model can respond with. It defaults to `["audio"]`,... |
| model | body | string | No | The Realtime model used for this session.  |
| instructions | body | string | No | The default system instructions (i.e. system message) prepended to model call... |
| audio | body | object | No | Configuration for input and output audio.  |
| include | body | string[] | No | Additional fields to include in server outputs.  `item.input_audio_transcript... |
| tracing | body | string | No | Realtime API can write session traces to the [Traces Dashboard](https://platf... |
Other params: tools, tool_choice, parallel_tool_calls, reasoning, max_output_tokens, truncation, prompt

## Response example
null

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

POST

POST /realtime/calls/{call_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
→ 370 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/realtime/calls/call-id/accept' \  -H "Authorization: Bearer $OPENAI_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "type": "realtime"}'

Parameters

Name	In	Type	Required	Description
call_id	path	string	Yes	The identifier for the call provided in the [`realtime.call.incoming`](https://developers.openai.com/api/reference/resources/webhooks#realtime.call.incoming) webhook.
type	body	string	Yes	The type of session to create. Always `realtime` for the Realtime API.
output_modalities	body	string[]	No	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.
model	body	string	No	The Realtime model used for this session.
instructions	body	string	No	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.
audio	body	object	No	Configuration for input and output audio.
include	body	string[]	No	Additional fields to include in server outputs. `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.
tracing	body	string	No	Realtime API can write session traces to the [Traces Dashboard](https://platform.openai.com/logs?api=traces). Set to null to disable tracing. Once tracing is enabled for a session, the configuration cannot be modified. `auto` will create a trace for the session with default values for the workflow name, group id, and metadata.
tools	body	object[]	No	Tools available to the model.
tool_choice	body	string	No	How the model chooses tools. Provide one of the string modes or force a specific function/MCP tool.
parallel_tool_calls	body	boolean	No	Whether the model may call multiple tools in parallel. Only supported by reasoning Realtime models such as `gpt-realtime-2`.
reasoning	body	object	No	Configuration for reasoning-capable Realtime models such as `gpt-realtime-2`.
max_output_tokens	body	integer	No	Maximum number of output tokens for a single assistant response, inclusive of tool calls. Provide an integer between 1 and 4096 to limit output tokens, or `inf` for the maximum available tokens for a given model. Defaults to `inf`.
truncation	body	string	No	When the number of tokens in a conversation exceeds the model's input token limit, the conversation be truncated, meaning messages (starting from the oldest) will not be included in the model's context. A 32k context model with 4,096 max output tokens can only include 28,224 tokens in the context before truncation occurs. Clients can configure truncation behavior to truncate with a lower max token limit, which is an effective way to control token usage and cost. Truncation will reduce the number of cached tokens on the next turn (busting the cache), since messages are dropped from the beginning of the context. However, clients can also configure truncation to retain messages up to a fraction of the maximum context size, which will reduce the need for future truncations and thus improve the cache rate. Truncation can be disabled entirely, which means the server will never truncate but would instead return an error if the conversation exceeds the model's input token limit.
prompt	body	object	No	Reference to a prompt template and its variables. [Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code).

Response 200 OK

null

Get a free OpenAI API key → sponsored

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