> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gradium.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Speech-to-Speech Overview

> What Speech-to-Speech does and how to set it up

Gradium Speech-to-Speech (S2S) translates spoken audio from one language
into spoken audio in another, over a single duplex WebSocket. The input
audio is transcribed, translated into the target language, and
re-synthesized as output audio. You stream audio in and receive both the
synthesized output audio and the translated transcript back as they're
produced.

## Model

The only currently supported S2S model is **live translation**. To use
it, send a `setup` message with `model_name` set to `"s2s-translate"`,
`stt_model_name` set to `"stt-translate"`, and `tts_model_name` set to
`"default"`. Choose the target language
with `target_language` in `json_config`, and the output voice with
`voice_id` (required; it must be a voice in the target language).

```json theme={null}
{
  "type": "setup",
  "model_name": "s2s-translate",
  "stt_model_name": "stt-translate",
  "tts_model_name": "default",
  "input_format": "pcm",
  "output_format": "pcm",
  "voice_id": "YTpq7expH9539ERJ",
  "json_config": { "target_language": "en" }
}
```

You can try live translation without writing code in
[Gradium Studio](https://studio.gradium.ai/). In your own app, it is
available through the API only.

For the full list of fields and formats, see
[Speech-to-Speech Settings](https://docs.gradium.ai/guides/speech-to-speech-settings.md).

## Next steps

> [card] [Use the WebSocket API](https://docs.gradium.ai/guides/speech-to-speech.md)
>
> Stream audio in, output audio and transcript out, real-time or
> buffered.

> [card] [S2S settings](https://docs.gradium.ai/guides/speech-to-speech-settings.md)
>
> `voice_id`, `target_language`, inner model selection, formats.

> [card] [S2S WebSocket reference](https://docs.gradium.ai/api-reference/endpoint/s2s-websocket.md)
>
> Complete wire-level schema: every message type, every field, every
> error code.

> [card] [Voices](https://docs.gradium.ai/guides/voices/overview.md)
>
> Pick the voice used for the synthesized output.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.