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

# Audio

> Call POST /{consumer}/v1/audio/speech (TTS, raw bytes) and /v1/audio/transcriptions (STT, multipart). TrustGate routes only to registries that can speak or transcribe.

Clients send the same OpenAI Audio requests they would send to OpenAI. Auth and the
consumer slug are the same as [chat](/trustgate/getting-started/quickstart#call-from-your-application).

```bash theme={null}
curl -X POST "https://<gateway-host>/<consumer-slug>/v1/audio/speech" \
  -H "X-AG-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "Hello from TrustGate",
    "voice": "alloy"
  }' \
  --output speech.mp3
```

Speech returns **raw audio bytes** with the upstream `Content-Type` (for example `audio/mpeg`).
TrustGate does not wrap the body in JSON.

Transcriptions are multipart, same host and key:

```bash theme={null}
curl -X POST "https://<gateway-host>/<consumer-slug>/v1/audio/transcriptions" \
  -H "X-AG-API-Key: <your-api-key>" \
  -F model=whisper-1 \
  -F file=@speech.mp3
```

On a Private data plane, add `X-AG-Gateway-Slug` as in the chat snippets.

`GET` is rejected with **400**. `/v1/audio/translations` and extra path tails are **404**.

OpenAI SDKs use the same consumer base URL: `client.audio.speech.create()` and
`client.audio.transcriptions.create()`.

## Providers

| Registry                       | Speech (TTS)                                                       | Transcriptions (STT)              |
| ------------------------------ | ------------------------------------------------------------------ | --------------------------------- |
| **OpenAI**                     | `{base_url or https://api.openai.com/v1}/audio/speech`             | `.../audio/transcriptions`        |
| **Azure OpenAI**               | `{endpoint}/openai/deployments/{model}/audio/speech?api-version=…` | `.../audio/transcriptions`        |
| **Custom / OpenAI-compatible** | `{base_url}/audio/speech`                                          | `{base_url}/audio/transcriptions` |
| **OpenRouter**                 | `https://openrouter.ai/api/v1/audio/speech`                        | `.../audio/transcriptions`        |
| **Groq**                       | `https://api.groq.com/openai/v1/audio/speech`                      | `.../audio/transcriptions`        |
| **Mistral**                    | `https://api.mistral.ai/v1/audio/speech`                           | `.../audio/transcriptions`        |

Mistral speech uses `voice_id` upstream. If the client sends OpenAI `voice`, TrustGate copies
it to `voice_id`. Mistral's JSON `{audio_data}` (base64) is unwrapped to raw bytes so the
gateway response stays OpenAI-shaped.

xAI voice is a different wire (`/v1/tts`, `/v1/stt`). Anthropic, Gemini / Vertex, Bedrock,
Cohere, DeepSeek, Cerebras, and other chat-only providers do not expose these routes. They
are left out of the candidate pool.

Chat `input_audio` parts are a different surface.

The JSON `model` field is allowlisted as usual. For multipart transcriptions, TrustGate
reads the form `model` field for allowlists, Azure deployment names, and `@provider/model`
pins. It does **not** rewrite the multipart body.

## Routing

1. The consumer's registries are filtered to those that advertise the matching capability
   (`audio_speech` or `audio_transcription`).
2. [Model resolution](/trustgate/routing/model-resolution) and
   [load balancing](/trustgate/routing/load-balancing) run on that pool.
3. Pinning a registry that cannot serve that audio path is a **400**, not a failover — including
   `@provider/model` in a multipart `model` field.
4. An empty capable pool is a **503**.

Attach at least one audio-capable registry to the consumer. A mixed chat + audio pool is
fine: chat still uses every chat-capable member; speech and transcriptions skip the rest.

## Related

* [Registries](/trustgate/concepts/registries)
* [Consumers](/trustgate/concepts/consumers) — Connect tab
* [Embeddings](/trustgate/routing/embeddings)
* [Images](/trustgate/routing/images)
* [Files](/trustgate/routing/files)
* [Models](/trustgate/routing/models)
* [Quickstart](/trustgate/getting-started/quickstart)