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

> ## Agent Instructions
> Public hosts only: console https://omnimux.ai/dashboard · API https://api.omnimux.ai · docs https://docs.omnimux.ai.
> Gateway auth is Authorization: Bearer sk-… on https://api.omnimux.ai/v1 (OpenAI-compatible Chat Completions and related paths).
> Discover pages from /llms.txt; full site dump /llms-full.txt; product skill /skill.md; docs search MCP /mcp. Prefer .md page URLs for Markdown.
> Default docs locale is en; zh mirrors the same relative paths. Do not invent model ids not present on live pricing or the complete API pages.

# Seed Audio Generation

> VolcEngine / BytePlus Seed Audio speech and sound effects · model `seed-audio-1.0`

* Endpoint: `POST /v1/audio/speech` with `model` `seed-audio-1.0`
* Protocol: OpenAI-compatible Audio Speech (TTS) endpoint
* Supports text-to-speech synthesis, timbre reference, and scene sound design up to 120 seconds per generation

## Identity

| Field  | Value                 |
| ------ | --------------------- |
| Series | Audio series          |
| Brand  | VolcEngine / BytePlus |
| model  | `seed-audio-1.0`      |

## Endpoint

| Method | Path               |
| ------ | ------------------ |
| `POST` | `/v1/audio/speech` |

Base URL: `https://api.omnimux.ai`

## Authorizations

| Name            | In     | Type   | Required | Description               |
| --------------- | ------ | ------ | -------- | ------------------------- |
| `Authorization` | header | string | yes      | `Bearer sk-...` (API key) |

## Body

| Field             | Type   | Required | Description                                                   |
| ----------------- | ------ | -------- | ------------------------------------------------------------- |
| `model`           | string | yes      | Must be `seed-audio-1.0`                                      |
| `input`           | string | yes      | The text to synthesize into audio, up to 3000 characters      |
| `voice`           | string | no       | Voice identifier (preset timbre ID or cloned voice ID)        |
| `response_format` | string | no       | Audio format (`wav`, `mp3`, `pcm`, `ogg_opus`). Default `wav` |
| `speed`           | number | no       | Playback speed multiplier \[0.25, 4.0]. Default `1.0`         |

## Response

### 200

Returns binary audio data stream (with `Content-Type: audio/wav` etc.).

<Panel>
  <RequestExample>
    ```bash curl theme={null}
    curl --request POST \
      --url https://api.omnimux.ai/v1/audio/speech \
      --header 'Authorization: Bearer sk-...' \
      --header 'Content-Type: application/json' \
      --data '{
        "model": "seed-audio-1.0",
        "input": "Welcome to VolcEngine Seed Audio synthesis.",
        "voice": "zh_female_cancan",
        "response_format": "mp3"
      }' \
      --output output.mp3
    ```
  </RequestExample>

  <ResponseExample>
    ```http 200 OK theme={null}
    Content-Type: audio/mpeg
    Content-Length: 48291

    <binary audio data>
    ```
  </ResponseExample>
</Panel>