> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # Gemini 3.8 Flash TTS > Google's studio-grade text-to-speech: rich, expressive delivery, stable long-form narration, and 130+ languages (detected automatically). Turns text into speech and returns a **WAV** URL (24 kHz, mono). The `text` is read **verbatim** — put delivery directions such as tone or pace in `style`, not in the text, or they will be read aloud. Short vocal events and pauses can go inline in angle brackets, e.g. `Wait... did you hear that? `. **Pricing** — billed by text length, not by audio duration: | Unit | Tokens | USD | |---|---|---| | every 200 characters (rounded up) | 2.63 | $0.0526 | A 350-character request is billed as 2 units (5.26 tokens = $0.1052). Anything from 1 to 200 characters costs 1 unit. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated audio. The result arrives as a `json` array item with `type: "audio"` and a WAV URL in `value`. ## OpenAPI ````yaml api-reference/audio-generations/openapi-gemini-3-8-flash-tts.json POST /api/v1/audio/generations openapi: 3.1.0 info: title: GoEnhance API - Gemini 3.8 Flash TTS description: Gemini 3.8 Flash TTS version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/audio/generations: post: tags: - AudioGenerations summary: Gemini 3.8 Flash TTS description: >- Google's studio-grade text-to-speech: rich, expressive delivery, stable long-form narration, and 130+ languages (detected automatically). Turns text into speech and returns a **WAV** URL (24 kHz, mono). The `text` is read **verbatim** — put delivery directions such as tone or pace in `style`, not in the text, or they will be read aloud. Short vocal events and pauses can go inline in angle brackets, e.g. `Wait... did you hear that? `. **Pricing** — billed by text length, not by audio duration: | Unit | Tokens | USD | |---|---|---| | every 200 characters (rounded up) | 2.63 | $0.0526 | A 350-character request is billed as 2 units (5.26 tokens = $0.1052). Anything from 1 to 200 characters costs 1 unit. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated audio. The result arrives as a `json` array item with `type: "audio"` and a WAV URL in `value`. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - gemini-3-8-flash-tts description: Model name. Must be `gemini-3-8-flash-tts`. text: type: string minLength: 1 maxLength: 4000 description: >- Text to synthesize, read verbatim. Required. Max 4000 characters. Billing is based on this length. A single request can produce about 8 minutes of audio; very slow styles on long texts can hit that limit, in which case the task fails and is refunded — split the text into shorter parts. voice: type: string description: >- Voice. Optional — defaults to `Kore`. One of the 30 prebuilt voices (case-insensitive): `Kore`, `Zephyr`, `Puck`, `Charon`, `Fenrir`, `Leda`, `Orus`, `Aoede`, `Callirrhoe`, `Autonoe`, `Enceladus`, `Iapetus`, `Umbriel`, `Algieba`, `Despina`, `Erinome`, `Algenib`, `Rasalgethi`, `Laomedeia`, `Achernar`, `Alnilam`, `Schedar`, `Gacrux`, `Pulcherrima`, `Achird`, `Zubenelgenubi`, `Vindemiatrix`, `Sadachbia`, `Sadaltager`, `Sulafat` — or a voice id from the Gemini voice library, such as `en-us-advisor-1` (browse the full library in Google AI Studio). All voices can speak any supported language. style: type: string maxLength: 500 description: >- Optional. A short natural-language description of the delivery for the whole text — tone, emotion, pace or volume, e.g. `warm and upbeat`, `whispered urgently`, `speaking slowly and calmly`. Leave it out for a natural read. There is no `speed` parameter; describe the pace here instead. Slower styles produce longer audio for the same text. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - text example: model: gemini-3-8-flash-tts text: >- Welcome to GoEnhance. Let's build something great today. voice: Kore style: warm and upbeat responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string cost: type: number description: >- Tokens deducted for this request. This is the amount actually charged, so it already reflects any discount active on your account and can be lower than the listed price. Tokens are deducted when the task is accepted, and refunded automatically if the generation ends in failure. example: 2.63 required: - img_uuid - cost required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 cost: 2.63 '2': summary: Insufficient tokens value: code: 100 msg: tokens is not enough quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string headers: {} deprecated: false ````