Audio Speech

Synthesize speech from text using AI voices.

POST/api/v1/audio/speech

Request Body

Parameter	Type	Required	Description
model	string	Yes	Model key (see models below)
prompt	string	Yes	Text to synthesize into speech
params	object	No	Model-specific parameters

Response

{
  "inferenceJobId": "ij_..."
}

Example

POST/api/v1/audio/speech

{
  "model": "elevenlabs-tts",
  "prompt": "Welcome to Wonda, the AI-powered video editing platform.",
  "params": {
    "voiceId": "voice_abc123",
    "stability": 0.5,
    "similarityBoost": 0.75
  }
}

Models

elevenlabs-tts

Text-to-speech via ElevenLabs. Prompt is the text to synthesize.

Parameter	Type	Required	Description
voiceId	string	Yes	ElevenLabs voice identifier
stability	number	No	Voice stability (0 to 1)
similarityBoost	number	No	Similarity boost (0 to 1)

Attachments: None.