Audio

Generate speech

Convert text into speech, store the result privately, and download it with the same API key.

Create speech

Speech completes in the request and returns a private MP3 file URL.

POST/v1/speech/generations

Bearer authentication required

cURL

curl https://api.byta-ai.com/v1/speech/generations \
  -H "Authorization: Bearer $BYTA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Byta-Audio-1.1",
    "input": "Welcome to Byta AI.",
    "voice": "alloy",
    "language": "en",
    "speed": 1
  }'

200 OK

{
  "id": "d07144aaddd8420ab9d0ea4d8aaa352f",
  "object": "speech_generation",
  "status": "completed",
  "modelId": "Byta-Audio-1.1",
  "creditsCharged": 1,
  "audio": {
    "id": "cc85a3897a3545878755290b24e2d4b4",
    "mimeType": "audio/mpeg",
    "sizeBytes": 184320,
    "url": "https://api.byta-ai.com/v1/speech/generations/d071.../files/cc85..."
  }
}

Parameters

inputrequired

string

Text to speak, up to 4,096 characters.

modeloptional

string

An enabled speech model from GET /v1/models.

voiceoptional

string

A supported voice identifier, up to 128 characters.

languageoptional

string

Supported language code. Defaults to en.

speedoptional

number

Playback speed from 0.25 through 4.0.

Download audio

GET/v1/speech/generations/{generationId}/files/{fileId}

Use the same Bearer key; add ?download=1 for attachment disposition.

Audio URLs are private

Do not expose the API key in a browser. Proxy or stream the file from your server.

Pricing

Model	Credits per 1,000 characters
`Byta-Audio-1.1`	15
`Byta-Audio-1.1-Pro`	20