Audio Speech

POST /v1/audio/speech

Convert text to natural-sounding speech in multiple voices and audio formats using OpenAI TTS models.

Request

POST https://api.chuizi.ai/v1/audio/speech

Authentication

Authorization: Bearer ck-your-api-key

Parameters

Parameter	Type	Required	Default	Description
`model`	string	Yes	—	Model name, e.g. `openai/tts-1`, `openai/tts-1-hd`
`input`	string	Yes	—	Text to convert to speech (max 4096 characters)
`voice`	string	Yes	—	Voice preset: `alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`

Request Example

config.json

json

{
  "model": "openai/tts-1",
  "input": "Hello! Welcome to Chuizi.AI, the unified AI gateway.",
  "voice": "nova",
  "response_format": "mp3",
  "speed": 1.0
}

Response

The response is a binary audio stream with the appropriate Content-Type header:

HTTP/1.1 200 OK
Content-Type: audio/mpeg
Transfer-Encoding: chunked

(binary audio data)

The response does not include a JSON body. Save the response body directly as an audio file.

Code Examples

terminal

bash

curl -X POST https://api.chuizi.ai/v1/audio/speech \
  -H "Authorization: Bearer ck-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/tts-1",
    "input": "Hello! Welcome to chuizi.ai.",
    "voice": "nova"
  }' \
  --output speech.mp3

Next Steps

Audio Transcriptions — convert speech back to text
Pricing — TTS model pricing details
Error Codes — troubleshoot common API errors