Gemini 3.1 Flash TTS

Endpoint

POST https://api.roasos.com/v1/audio/gemini-3.1-flash-tts

Send your API key as a bearer token. The key needs the scope api:write. Every paid request also needs an Idempotency-Key header.

The envelope fields quote_only, quote_id, webhook_url and wait_timeout_seconds behave the same on each model endpoint. Refer to Jobs and Quotes and credits.

Good at

A voice-over or a hook line that must sound a specific way. Write the delivery in style_instruction ("Warm and unhurried, like a friend recommending something") and keep text for the spoken words only. Inline audio tags such as [sigh], [laughing], [whispering], and [short pause] steer single moments. Two voices can speak in one take: send speakers with two { speaker_id, voice } entries and start every line of text with the alias and a colon (Host: ...). voice takes one of the 30 preset names; Kore is the default. language takes a BCP-47 code such as en-US or fr-FR; omit it and the model detects the language. It does not clone a voice and does not accept media of any kind.

Pricing

The unit is one characters. Pricing key: gemini-3.1-flash-tts.

The credits come from the roasOS pricing table. No other field changes the price. To get the exact price of your request, send it with quote_only: true first.

Modes

• text-to-speech

Provider endpoints: fal-ai/gemini-3.1-flash-tts.

Request fields

The schema is strict. A field that is not in this table gets 400 unsupported_option. The field names are the roasOS role names. One role has one name in every family.

Media

This endpoint accepts no media.

Every other role is refused: avatar_id, elements, product_id, product_images, references, reference_images, image_url, end_image_url, scene_id, scene_image, video_urls, video_url, audio_urls, audio_url, voice_id. A refused role gets 400 unsupported_option.

Prompt

text limit 5,000 characters; style_instruction limit 2,000. roasOS adds no wrapper.

• Put the delivery in style_instruction, not in text. The model speaks every word of text.
• Use one audio tag right before the words it changes. Too many tags make the read unstable.
• For two voices, make each alias match a speaker_id exactly, and start each line with it.
• Set language when the text mixes languages or when the accent matters.
• Choose the voice by its character (Kore firm, Puck upbeat, Charon informative, Zephyr bright, Aoede breezy), then let the direction do the rest.
• Lower temperature for a steady, repeatable read; raise it for a more varied one.

Not exposed

These catalog entries describe omitted inputs, pinned values and source constraints. They do not imply that the provider accepts every listed field.

• voice_id — pinned to the model has no provider voice-clone registry.
• references — not accepted by this public endpoint.
• avatar_id — not accepted by this public endpoint.
• product_id — not accepted by this public endpoint.
• audio_urls — not accepted by this public endpoint.
• image_url — not accepted by this public endpoint.
• speed — not accepted by this public endpoint.
• pitch — not accepted by this public endpoint.
• emotion — not accepted by this public endpoint.

Result

The result kind is audio. Always present: url. Present when the run makes it: timestamps.

{
  "data": {
    "id": "gen_…",
    "kind": "audio",
    "model": "gemini-3.1-flash-tts",
    "status": "completed",
    "result": {
      "timestamps": [
        {}
      ],
      "url": "https://cdn.roasos.com/workspaces/ws_01/result"
    }
  }
}

The files are immutable objects on https://cdn.roasos.com. A result URL is a valid media input for your next request.

Example

The three steps are always the same: quote, run, poll.

# 1. Quote. Nothing is spent.
curl -X POST https://api.roasos.com/v1/audio/gemini-3.1-flash-tts \
  -H "Authorization: Bearer roasos_sk_live_..." \
  -H "Idempotency-Key: 0f1c9e2a-gemini-3.1-flash-tts-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_only":true,"text":"Two drops, morning and night. That is the whole routine."}'
# 200 { "data": { "kind": "quote", "quote_id": "q_7Hk...", "credits": 1, "expires_at": "...",
#        "confirmation": { "model": "gemini-3.1-flash-tts", "example": "1000_characters" } } }

# 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only.
curl -X POST https://api.roasos.com/v1/audio/gemini-3.1-flash-tts \
  -H "Authorization: Bearer roasos_sk_live_..." \
  -H "Idempotency-Key: 0f1c9e2a-gemini-3.1-flash-tts-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_id":"q_7Hk...","text":"Two drops, morning and night. That is the whole routine."}'
# 201 { "data": { "id": "gen_...", "status": "queued", "credits_reserved": 1 } }

# 3. Poll, then read the result.
curl https://api.roasos.com/v1/jobs/gen_.../status -H "Authorization: Bearer roasos_sk_live_..."
curl https://api.roasos.com/v1/jobs/gen_.../result -H "Authorization: Bearer roasos_sk_live_..."

The deprecated path

POST /v1/generations still reaches this model for one minor version. It is deprecated. This is how it maps:

POST /v1/audio/gemini-3.1-flash-tts is the endpoint. POST /v1/generations also works with { "type": "audio", "model": "gemini-3.1-flash-tts", "prompt": "<text>", "options": { "voice": "Puck", "style_instruction": "Warm and amused.", "language": "en-GB" } }; there the script goes in prompt. options.speed, pitch, stability, and similarity_boost have no provider field and are accepted at their default values only.

See also

• llms.txt for this model — the same facts as one plain-text file for an agent.
• GET https://api.roasos.com/v1/catalog/gemini-3.1-flash-tts — the machine-readable form: enums, defaults, limits and prices. Refer to the API reference.
• Jobs — how to poll a job and read its result.
• Provider endpoints: fal-ai/gemini-3.1-flash-tts.