Text to Speech
Text to convert (max 5000 chars)
Voice ID to use for synthesis
Audio file for voice cloning (alternative to voice_id)
Quality preset for synthesis
3Output audio format (wav/mp3)
wavPossible values: Speech speed multiplier
1Target audio duration in seconds
0Target language code (e.g., "zh", "en", "zh+en")
Whether to enhance voice similarity
falseEmotion parameters as JSON string, e.g., {"Sadness":0.2, "Surprise":0.5}
Whether to trim leading and trailing silence from the generated audio
falseWhether to save the uploaded voice file
falseSuccess — returns audio binary stream
Invalid parameters or processing error
API Key missing or invalid
Payment required
Internal server error (TTS synthesis failure)
Text to enhance with emotions (max 5000 chars)
Success
Status code (0 = success)
Invalid request
API Key missing or invalid
Payment required
Hard limit exceeded
Last updated