Skip to content

Product

Start here

SDKs and libraries

Pricing and rate limits

Capabilities

Search grounding

Image understanding

Image generation

Video understanding

Media segmentation

Structured output

Protocols

Choosing an API

Chat Completions API

Cookbook

API fundamentals

Building with Muse Code

Muse Voice Transcribe

Muse Code

Authentication and billing

Permissions and safety

Working with the agent

Session messaging

Rewind a conversation

Configuration and context

Extending and automating

Muse Glimmer

Prompting guide

Speculative decoding

Run inference

Deploy with vLLM

Deploy with SGLang

Deploy with llama.cpp

Deploy with ExecuTorch

Run with Together AI

Customization

Fine-tuning (SFT)

Reinforcement learning

Agent guides

Agent frameworks

SAM

Segmenting with prompts

Reading segmentation output

Client libraries

API reference

Responses

Create a response

Retrieve a response

Delete a response

Cancel a response

Count input tokens

Chat completions

Create a chat completion

Messages

Create a message

Files

Retrieve a file

Retrieve file content

Images

Generate an image

Voice

Transcribe a recording

Transcribe in realtime

Models

Retrieve a model

Close search

Type to search the documentation.

↑↓Navigate↵SelectEscClose

Voice

The audio endpoints transcribe speech to text. Transcribe a complete recording in one request, or stream live audio over a WebSocket and receive transcripts as the audio arrives.

Transcribe a recording
Transcribe in realtime
Schemas

For modes, speaker labels, endpointing, and worked examples, see the Speech to text feature page.

On this page

Please confirm your identity

For added security, you need to confirm your identity. You will be taken to your single sign-on provider, where you can enter your password.