Text to Speech — OneHub

Text-to-speech via OpenAI. Returns raw audio bytes.

Docs

Docs Quick Start Authentication SDK Setup Available Models Rate Limits Chat Completions Streaming List Models Embeddings Image Generation Text to Speech Speech to Text Billing & Wallet Webhooks Errors

Text to Speech

POST https://www.onehub.design/v1/audio/speech

Request

curl https://www.onehub.design/v1/audio/speech \
  -H "Authorization: Bearer sk-onehub-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "input": "Hello from OneHub!",
    "voice": "alloy",
    "response_format": "mp3"
  }' --output speech.mp3

Parameters

Field	Type	Description
`model`	string	TTS model, e.g. `gpt-4o-mini-tts`
`input`	string	The text to speak (max 4096 chars)
`voice`	string	`alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`
`response_format`	string	`mp3`, `opus`, `aac`, `flac`, `wav`, `pcm`
`speed`	number	Speed 0.25–4.0. Default: 1.0

The response body is the raw audio file — save it with --output or stream it directly.