Audio Generation

Endpoints

POST https://routerbase.com/v1/audio/speech
POST https://routerbase.com/v1/audio/generations
GET  https://routerbase.com/v1/audio/generations/{id}

/v1/audio/speech — text-to-speech (ElevenLabs TTS).
/v1/audio/generations — general audio generation (sound effects, dialogue, etc.).
Both are asynchronous — they return an id and status: "pending". Poll GET /v1/audio/generations/{id} for the final result.

Request Headers

Header	Value
`Authorization`	`Bearer sk-rb-xxxxxxxxxxxx`
`Content-Type`	`application/json`

Text-to-Speech

Request Body

string

required

TTS model ID. e.g. elevenlabs/tts-turbo, elevenlabs/tts-multilingual.

string

required

Text to synthesize.

string

Voice ID for the model.

number

Playback speed multiplier. Default 1.0.

string

Optional. RouterBase will POST the final result to this URL.

Example

curl -X POST https://routerbase.com/v1/audio/speech \
  -H "Authorization: Bearer sk-rb-xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "elevenlabs/tts-turbo",
    "input": "Hello, world!",
    "voice": "rachel"
  }'

import requests

r = requests.post(
    "https://routerbase.com/v1/audio/speech",
    headers={"Authorization": "Bearer sk-rb-xxxxxxxxxxxx"},
    json={"model": "elevenlabs/tts-turbo", "input": "Hello, world!", "voice": "rachel"},
)
print(r.json()["id"])

Response

{
  "id": "a1b2c3d4-...",
  "object": "audio.generation",
  "status": "pending",
  "model": "elevenlabs/tts-turbo",
  "created": 1776245700
}

Audio Generation (sound effects, dialogue, music, etc.)

Request Body

string

required

Audio model ID. e.g. elevenlabs/sound-effect, elevenlabs/dialogue, elevenlabs/audio-isolation.

string

Text describing the desired audio. Required for sound effects / dialogue.

string

Required for elevenlabs/audio-isolation and elevenlabs/elevenlabs (speech-to-text). Source audio URL.

string

Optional callback URL.

Polling

GET /v1/audio/generations/{id}

When complete:

{
  "id": "a1b2c3d4-...",
  "object": "audio.generation",
  "status": "success",
  "model": "elevenlabs/tts-turbo",
  "data": [
    { "url": "https://media.routerbase.com/media/<user>/<gen>/0.mp3" }
  ],
  "created": 1776245700
}

`status`	Meaning
`pending`	Task is queued or running
`success`	Generation complete; `data[].url` is populated
`failed`	Generation failed

See Async Tasks for the polling pattern.

Get Started

API Reference

Endpoints

Request Headers

Text-to-Speech

Request Body

Example

Response

Audio Generation (sound effects, dialogue, music, etc.)

Request Body

Polling

​Endpoints

​Request Headers

​Text-to-Speech

​Request Body

​Example

​Response

​Audio Generation (sound effects, dialogue, music, etc.)

​Request Body

​Polling

Endpoints

Request Headers

Text-to-Speech

Request Body

Example

Response

Audio Generation (sound effects, dialogue, music, etc.)

Request Body

Polling