Gemini 3.1 Flash Text to speech

Endpoint

POST /audio/generations

Full URL: https://modelfold.ai/v1/audio/generations

Authentication: every request must include the Authorization: Bearer <API_KEY> header.

Send model parameters directly in the JSON body. Do not wrap them in input. This request waits for generation to finish and returns data[].url; supported media models also offer async jobs, polling and callbacks. Replace example media URLs with your own publicly accessible files. See API gateway for billing and errors.

Input parameters for the generation task

Request Parameters

Body (application/json)

Parameter	Type	Required	Description
model	string	Yes	Model to be used Default："google/gemini-3-1-flash-tts"。 Allowed values：google/gemini-3-1-flash-tts。 Example：google/gemini-3-1-flash-tts。
temperature	number	No	Sampling temperature, e.g., 1 Default：1。 minimum: 0. maximum: 2. Example：1。
scene	string	No	Scene description, e.g., "A quiet, warm room with a fireplace crackling softly." Default：""。 Example：``。
sample_context	string	No	Sample context/overall tone, e.g., "Audiobook style narration. Tone is gentle and inviting." Default：""。 Example：``。
speakers	array<object>	Yes	List of speaker configurations
speakers[].speaker_id	string	Yes	Speaker identifier, e.g., "Speaker 1" or "Speaker 2"; must be in the "Speaker N" format
speakers[].voice_name	string	Yes	Voice name, e.g., "Zephyr", "Fenrir", "Puck" Allowed values：Achernar / Achird / Algenib / Algieba / Alnilam / Aoede / Autonoe / Callirrhoe / Charon / Despina / Enceladus / Erinome / Fenrir / Gacrux / Iapetus / Kore / Laomedeia / Leda / Orus / Puck / Pulcherrima / Rasalgethi / Sadachbia / Sadaltager / Schedar / Sulafat / Umbriel / Vindemiatrix / Zephyr / Zubenelgenubi。 Example：Achernar。
speakers[].audio_profile	string	No	Audio profile description, e.g., "A warm and soothing narrator" or "A stern and weary gatekeeper"
speakers[].accent	string	Yes	Accent, e.g., "British (RP)" or "American (Gen)" Allowed values：Neutral / American (Gen) / American (Valley) / American (South) / British (RP) / British (Brixton) / Transatlantic / Australian。 Example：Neutral。
speakers[].style	string	No	Emotional style, e.g., "Whisper" or "Deadpan" Allowed values：Vocal Smile / Newscaster / Whisper / Empathetic / Promo/Hype / Deadpan。 Example：Vocal Smile。
speakers[].pace	string	No	Pace, e.g., "Staccato" or "Natural" Allowed values：Natural / Rapid Fire / The Drift / Staccato。 Example：Natural。
dialogue_turns	array<object>	Yes	List of dialogue turns, output in sequential order
dialogue_turns[].speaker_id	string	Yes	Corresponding speaker identifier, e.g., "Speaker 1"
dialogue_turns[].text	string	Yes	The text spoken by the speaker, which may contain tone tags, e.g., "Once upon a time, in a quiet valley hidden away..." maxLength: 10000.

Request Example

curl -X POST "https://modelfold.ai/v1/audio/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-3-1-flash-tts",
  "speakers": [
    {
      "speaker_id": "Speaker 1",
      "voice_name": "Achernar",
      "accent": "Neutral"
    }
  ],
  "dialogue_turns": [
    {
      "speaker_id": "Speaker 1",
      "text": "A paper boat drifting down a rainy street."
    }
  ],
  "temperature": 1,
  "scene": "example",
  "sample_context": "A paper boat drifting down a rainy street."
}'

{
  "model": "google/gemini-3-1-flash-tts",
  "speakers": [
    {
      "speaker_id": "Speaker 1",
      "voice_name": "Achernar",
      "accent": "Neutral"
    }
  ],
  "dialogue_turns": [
    {
      "speaker_id": "Speaker 1",
      "text": "A paper boat drifting down a rainy street."
    }
  ],
  "temperature": 1,
  "scene": "example",
  "sample_context": "A paper boat drifting down a rainy street."
}

Response

200 — Generation completed. usage contains actual billing details; result URLs are illustrative.

{
  "ok": true,
  "created": 1792134000,
  "data": [
    {
      "url": "https://modelfold.ai/uploads/outputs/result.mp3"
    }
  ],
  "usage": {}
}