Speech recognition

Developing

POST

/v1/audio/transcriptions

Supports speech recognition and is compatible with whisper-1, gpt-4o-transcribe, and gpt-4o-mini-transcribe.

Request

Header Params

Body Params multipart/form-data

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/audio/transcriptions' \
--header 'Authorization: {{Authorization}}' \
--form 'model="whisper-1"' \
--form 'file="input.wav"' \
--form 'response_format="json"'

Responses

🟢200成功

application/json

Bodyapplication/json

Example

{
    "text": "My initial assessment is that it may take about a day, so let's report it as about a day for now, okay?",
    "logprobs": null,
    "usage": null
}

Modified at 2026-10-19 10:10:04

Create chat completion with deepseek v3.1 level of reasoning (streaming)

Speech synthesis