--- title: "Gemini 3.1 Flash TTS" description: "Text-to-speech on Google Gemini 3.1 Flash TTS, with 30 preset voices and 87 languages. It is best at a voice-over that you direct in plain words: tone, pace, accent, and emotion. It is the lowest per-character voice price in the catalog." url: https://docs.roasos.com/models/audio/gemini-3.1-flash-tts --- # Gemini 3.1 Flash TTS Family `audio` · model `gemini-3.1-flash-tts` · catalog `model-catalog@2026-10-06.v5` · pricing `customer-pricing@2026-11-05.v15` . ## Endpoint ```http 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](/concepts/jobs) and [Quotes and credits](/concepts/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`. | Request | Credits | | ----------------- | ------- | | `1000_characters` | 1 | | `2000_characters` | 2 | | `5000_characters` | 3 | 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 | Field | Type | Required | Default | Rule | | ---------------------- | --------- | -------- | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `language` | enum | no | — | `ar-EG`, `bn-BD`, `nl-NL`, `en-IN`, `en-US`, `fr-FR`, `de-DE`, `hi-IN`, `id-ID`, `it-IT`, `ja-JP`, `ko-KR`, `mr-IN`, `pl-PL`, `pt-BR`, `ro-RO`, `ru-RU`, `es-ES`, `ta-IN`, `te-IN`, `th-TH`, `tr-TR`, `uk-UA`, `vi-VN`, `af-ZA`, `sq-AL`, `am-ET`, `ar-001`, `hy-AM`, `az-AZ`, `eu-ES`, `be-BY`, `bg-BG`, `my-MM`, `ca-ES`, `ceb-PH`, `cmn-CN`, `cmn-TW`, `hr-HR`, `cs-CZ`, `da-DK`, `en-AU`, `en-GB`, `et-EE`, `fil-PH`, `fi-FI`, `fr-CA`, `gl-ES`, `ka-GE`, `el-GR`, `gu-IN`, `ht-HT`, `he-IL`, `hu-HU`, `is-IS`, `jv-JV`, `kn-IN`, `kok-IN`, `lo-LA`, `la-VA`, `lv-LV`, `lt-LT`, `lb-LU`, `mk-MK`, `mai-IN`, `mg-MG`, `ms-MY`, `ml-IN`, `mn-MN`, `ne-NP`, `nb-NO`, `nn-NO`, `or-IN`, `ps-AF`, `fa-IR`, `pt-PT`, `pa-IN`, `sr-RS`, `sd-IN`, `si-LK`, `sk-SK`, `sl-SI`, `es-419`, `es-MX`, `sw-KE`, `sv-SE`, `ur-PK` | | `output_format` | enum | no | `mp3` | `mp3`, `wav`, `ogg_opus` | | `quote_id` | string | no | — | UUID | | `quote_only` | boolean | no | `false` | — | | `speakers` | object\[] | no | — | 1–2 items; each `{ speaker_id, voice }` | | `style_instruction` | string | no | — | ≥ 1 character; ≤ 2,000 characters | | `temperature` | number | no | `1` | 0–2 | | `text` | string | yes | — | ≥ 1 character; ≤ 5,000 characters | | `voice` | enum | no | `Kore` | `Kore`, `Puck`, `Charon`, `Zephyr`, `Aoede`, `Fenrir`, `Leda`, `Orus`, `Callirrhoe`, `Autonoe`, `Enceladus`, `Iapetus`, `Umbriel`, `Algieba`, `Despina`, `Erinome`, `Algenib`, `Rasalgethi`, `Laomedeia`, `Achernar`, `Alnilam`, `Schedar`, `Gacrux`, `Pulcherrima`, `Achird`, `Zubenelgenubi`, `Vindemiatrix`, `Sadachbia`, `Sadaltager`, `Sulafat` | | `wait_timeout_seconds` | integer | no | `0` | 0–60 | | `webhook_url` | string | no | — | https URL; ≤ 4,096 characters | 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`. Each media URL must be an immutable object on `https://cdn.roasos.com` that your workspace owns. Any other URL gets `400 reference_media_not_workspace_owned` . Refer to [Reference media and uploads](/concepts/reference-media) to learn how to put a file there. ## 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`. ```json { "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. cURL JavaScript Python ```bash # 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_..." ``` ```javascript const key = process.env.ROASOS_API_KEY; const url = "https://api.roasos.com/v1/audio/gemini-3.1-flash-tts"; const idempotencyKey = "0f1c9e2a-gemini-3.1-flash-tts-0001"; const input = { "text": "Two drops, morning and night. That is the whole routine." }; const post = (payload) => fetch(url, { method: "POST", headers: { Authorization: `Bearer ${key}`, "Idempotency-Key": idempotencyKey, "Content-Type": "application/json", }, body: JSON.stringify(payload), }).then((response) => response.json()); // 1. Quote. Nothing is spent. const quote = await post({ quote_only: true, ...input }); console.log(quote.data.credits); // 2. Run. const job = await post({ quote_id: quote.data.quote_id, ...input }); // 3. Poll, then read the result. let status = "queued"; while (status !== "completed" && status !== "failed" && status !== "canceled") { await new Promise((done) => setTimeout(done, 3000)); const poll = await fetch(`${url.split("/v1")[0]}/v1/jobs/${job.data.id}/status`, { headers: { Authorization: `Bearer ${key}` }, }).then((response) => response.json()); status = poll.data.status; } const result = await fetch(`${url.split("/v1")[0]}/v1/jobs/${job.data.id}/result`, { headers: { Authorization: `Bearer ${key}` }, }).then((response) => response.json()); console.log(result.data.result); ``` ```python import os, time, requests key = os.environ["ROASOS_API_KEY"] url = "https://api.roasos.com/v1/audio/gemini-3.1-flash-tts" headers = { "Authorization": f"Bearer {key}", "Idempotency-Key": "0f1c9e2a-gemini-3.1-flash-tts-0001", } payload = { "text": "Two drops, morning and night. That is the whole routine." } # 1. Quote. Nothing is spent. quote = requests.post(url, headers=headers, json={"quote_only": True, **payload}).json() print(quote["data"]["credits"]) # 2. Run. job = requests.post(url, headers=headers, json={"quote_id": quote["data"]["quote_id"], **payload}).json() job_id = job["data"]["id"] # 3. Poll, then read the result. jobs = "https://api.roasos.com/v1/jobs" status = "queued" while status not in ("completed", "failed", "canceled"): time.sleep(3) status = requests.get(f"{jobs}/{job_id}/status", headers=headers).json()["data"]["status"] result = requests.get(f"{jobs}/{job_id}/result", headers=headers).json() print(result["data"]["result"]) ``` ## 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": "", "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](https://docs.roasos.com/models/audio/gemini-3.1-flash-tts/llms.txt) — 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](/api-reference/overview). * [Jobs](/concepts/jobs) — how to poll a job and read its result. * Provider endpoints: `fal-ai/gemini-3.1-flash-tts`.