OpenAI Audio API
API for speech-to-text transcription and text-to-speech generation.
OpenAPI Specification
openapi: 3.1.0
info:
title: OpenAI APIs OpenAI Audio API
description: >-
API for speech-to-text transcription, translation, and text-to-speech
generation. Uses the Whisper model for transcription and translation,
and the TTS model for speech synthesis.
version: '1.0'
contact:
name: OpenAI Support
email: [email protected]
url: https://help.openai.com
termsOfService: https://openai.com/policies/terms-of-use
externalDocs:
description: OpenAI Audio API Documentation
url: https://platform.openai.com/docs/api-reference/audio
servers:
- url: https://api.openai.com/v1
description: OpenAI Production API
tags:
- name: Speech
description: Text-to-speech operations
- name: Transcription
description: Speech-to-text transcription operations
- name: Translation
description: Audio translation operations
security:
- bearerAuth: []
paths:
/audio/speech:
post:
operationId: createSpeech
summary: OpenAI APIs Create speech
description: >-
Generates audio from the input text using the specified voice and model.
tags:
- Speech
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateSpeechRequest'
responses:
'200':
description: Audio file containing the generated speech
content:
audio/mpeg:
schema:
type: string
format: binary
audio/opus:
schema:
type: string
format: binary
audio/aac:
schema:
type: string
format: binary
audio/flac:
schema:
type: string
format: binary
audio/wav:
schema:
type: string
format: binary
audio/pcm:
schema:
type: string
format: binary
'400':
description: Invalid request
'401':
description: Unauthorized - invalid or missing API key
'429':
description: Rate limit exceeded
/audio/transcriptions:
post:
operationId: createTranscription
summary: OpenAI APIs Create transcription
description: >-
Transcribes audio into the input language as text using the Whisper model.
tags:
- Transcription
requestBody:
required: true
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/CreateTranscriptionRequest'
responses:
'200':
description: Transcription response
content:
application/json:
schema:
$ref: '#/components/schemas/TranscriptionResponse'
'400':
description: Invalid request
'401':
description: Unauthorized - invalid or missing API key
'429':
description: Rate limit exceeded
/audio/translations:
post:
operationId: createTranslation
summary: OpenAI APIs Create translation
description: >-
Translates audio into English text using the Whisper model.
tags:
- Translation
requestBody:
required: true
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/CreateTranslationRequest'
responses:
'200':
description: Translation response
content:
application/json:
schema:
$ref: '#/components/schemas/TranslationResponse'
'400':
description: Invalid request
'401':
description: Unauthorized - invalid or missing API key
'429':
description: Rate limit exceeded
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: API Key
description: OpenAI API key passed as a Bearer token
schemas:
CreateSpeechRequest:
type: object
required:
- model
- input
- voice
properties:
model:
type: string
description: The TTS model to use (tts-1 or tts-1-hd)
examples:
- tts-1
input:
type: string
maxLength: 4096
description: The text to generate audio for
voice:
type: string
enum:
- alloy
- echo
- fable
- onyx
- nova
- shimmer
description: The voice to use when generating the audio
response_format:
type: string
enum:
- mp3
- opus
- aac
- flac
- wav
- pcm
default: mp3
description: The format of the audio output
speed:
type: number
minimum: 0.25
maximum: 4.0
default: 1.0
description: The speed of the generated audio
CreateTranscriptionRequest:
type: object
required:
- file
- model
properties:
file:
type: string
format: binary
description: >-
The audio file to transcribe (flac, mp3, mp4, mpeg, mpga, m4a,
ogg, wav, or webm)
model:
type: string
description: The model to use for transcription (whisper-1)
examples:
- whisper-1
language:
type: string
description: The language of the input audio in ISO-639-1 format
prompt:
type: string
description: Optional text to guide the model's style or continue a previous segment
response_format:
type: string
enum:
- json
- text
- srt
- verbose_json
- vtt
default: json
description: The format of the transcription output
temperature:
type: number
minimum: 0
maximum: 1
default: 0
description: Sampling temperature between 0 and 1
timestamp_granularities:
type: array
items:
type: string
enum:
- word
- segment
description: The timestamp granularities to populate
CreateTranslationRequest:
type: object
required:
- file
- model
properties:
file:
type: string
format: binary
description: The audio file to translate
model:
type: string
description: The model to use for translation (whisper-1)
examples:
- whisper-1
prompt:
type: string
description: Optional text to guide the model's style
response_format:
type: string
enum:
- json
- text
- srt
- verbose_json
- vtt
default: json
description: The format of the translation output
temperature:
type: number
minimum: 0
maximum: 1
default: 0
description: Sampling temperature between 0 and 1
TranscriptionResponse:
type: object
properties:
text:
type: string
description: The transcribed text
task:
type: string
description: The task performed (transcribe)
language:
type: string
description: The detected or specified language
duration:
type: number
description: The duration of the audio in seconds
words:
type: array
items:
type: object
properties:
word:
type: string
start:
type: number
end:
type: number
description: Word-level timestamps (when requested)
segments:
type: array
items:
type: object
properties:
id:
type: integer
start:
type: number
end:
type: number
text:
type: string
description: Segment-level timestamps (when requested)
TranslationResponse:
type: object
properties:
text:
type: string
description: The translated text in English