> ## Documentation Index
> Fetch the complete documentation index at: https://deepl-c950b784-docs-language-table-from-v3.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# DeepL Voice API

> Transcribe and translate spoken audio in real time with the DeepL Voice API. Find the streaming guide, core concepts, and language and format reference.

The DeepL Voice API transcribes and translates spoken audio in real time over a WebSocket connection. Within a single streaming session, you can:

* Send one audio stream
* Receive transcripts in the source language
* Receive translations in multiple target languages
* <Badge color="green">closed beta</Badge> Receive translated speech

<Info>
  **Speech-to-text** (real-time transcription and text translation) is available to all customers with a paid DeepL API subscription. **Speech-to-speech** (translated TTS output) is a separate capability in closed beta and not included in standard API subscriptions.

  The provisions applying to DeepL API Enterprise subscriptions also apply to Voice API speech-to-text, with [additions to the Terms and Conditions, Service Specification, and Data Processing Agreement](/api-reference/voice/deepl-voice-api-service-specification-updates) (new sub-processors have been added to serve specific languages).
</Info>

## Start here

<CardGroup cols={2}>
  <Card title="Real-Time Voice Quickstart" icon="waveform-lines" href="/docs/voice/real-time-voice-quickstart">
    Create a session, stream audio over WebSocket, and handle reconnections, with a complete Python example.
  </Card>

  <Card title="Understanding Voice Sessions" icon="lightbulb" href="/docs/voice/understanding-voice-sessions">
    Understand the session flow, token lifecycle, and how audio and results are delivered.
  </Card>

  <Card title="Message Encoding" icon="binary" href="/docs/voice/message-encoding">
    Choose between JSON and MessagePack for WebSocket messages.
  </Card>

  <Card title="Supported Languages, Formats, and Limits" icon="table-list" href="/docs/voice/supported-languages-formats-and-limits">
    Check language availability, supported audio codecs and containers, and session limits.
  </Card>

  <Card title="API reference" icon="code" href="/api-reference/voice/request-session">
    Full request, message, and response schemas for the Voice API endpoints.
  </Card>
</CardGroup>

## Customization

Two optional features let you tailor transcription and translation to your domain:

* <Badge color="blue">beta</Badge> **Spoken terms**: improve transcription of frequently used terms such as company-specific terminology, acronyms, product names, and team member names. Manage them in [DeepL Home](https://www.deepl.com/en/voice/spoken-terms); management via API is coming soon.
* **Glossaries**: enforce specific translations for terms in the target language. Manage them in [DeepL Home](https://www.deepl.com/en/glossary) or programmatically with the [Glossaries API](/api-reference/multilingual-glossaries).

## Code examples

A reference implementation in Python is available in the [DeepL Python library repository](https://github.com/DeepLcom/deepl-python/tree/main/examples/voice/cli). The official DeepL SDKs don't integrate the Voice API yet, but you can use any WebSocket client library to interact with it.