> ## Documentation Index > Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt > Use this file to discover all available pages before exploring further. # Gemini 3.8 Flash Lite TTS > [Core Function] Gemini 3.8 Flash Lite TTS is Google's text-to-speech model for low-latency speech generation. [Strengths] Single-speaker synthesis, two-speaker dialogue, 101 languages, per-turn style control, and WAV output (24 kHz mono PCM). [Best For] Bulk narration, voice-agent responses, read-aloud features, and multilingual dialogue. [Limitations] Do NOT use this for streaming, voice creation, music generation, or audio, image, or video input. Dialogue requires exactly two speakers with prebuilt or extended-library voices; designed or replicated voices are limited to single-speaker synthesis. Combined text and style must stay within 8,192 Unicode characters. [Routing] Choose Flash Lite for latency and cost efficiency; choose Gemini 3.8 Flash TTS for expressive delivery and broader language coverage. ## Billing Billed in **USD per million input characters**. Current prices are listed on the [Modellix Pricing Page](https://www.modellix.ai/pricing). * **Single speaker:** Count Unicode characters in `text`. * **Two speakers:** Sum Unicode characters in all `turns[].text`, without adding separators. * `style`, speaker names, voice names, and `language_code` are excluded from the character count. ## OpenAPI ````yaml /media-model-api/google/google-t2s.json post /google/gemini-3.8-flash-lite-tts openapi: 3.1.0 info: title: Google Text-to-Speech Models API description: >- Google Gemini text-to-speech. Converts plain text into controllable speech audio. Submit an async task, then poll GET /api/v1/tasks/{task_id} for the audio. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai servers: - url: https://api.modellix.ai/api/v1 description: The text-to-speech models API from Google. security: - bearerAuth: [] paths: /google/gemini-3.8-flash-lite-tts: post: summary: Gemini 3.8 Flash Lite TTS description: >- [Core Function] Gemini 3.8 Flash Lite TTS is Google's text-to-speech model for low-latency speech generation. [Strengths] Single-speaker synthesis, two-speaker dialogue, 101 languages, per-turn style control, and WAV output (24 kHz mono PCM). [Best For] Bulk narration, voice-agent responses, read-aloud features, and multilingual dialogue. [Limitations] Do NOT use this for streaming, voice creation, music generation, or audio, image, or video input. Dialogue requires exactly two speakers with prebuilt or extended-library voices; designed or replicated voices are limited to single-speaker synthesis. Combined text and style must stay within 8,192 Unicode characters. [Routing] Choose Flash Lite for latency and cost efficiency; choose Gemini 3.8 Flash TTS for expressive delivery and broader language coverage. operationId: gemini38FlashLiteTTSAsync requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Gemini38FlashLiteTTSRequest' examples: single_speaker: summary: Single speaker with turn style value: text: Have a wonderful day! style: cheerful and friendly language_code: en-us voice: Kore dual_speaker: summary: Two-speaker dialogue, one part per turn value: language_code: en-us speakers: - speaker: Joe voice: Puck - speaker: Jane voice: Kore turns: - speaker: Joe text: How is it going today, Jane? style: cheerful and friendly - speaker: Jane text: Pretty good. Ready when you are. style: calm and relaxed responses: '200': description: >- Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; synthesized audio is returned on the task result. content: application/json: schema: $ref: '#/components/schemas/AsyncTaskResponse' example: code: 0 message: success data: status: pending task_id: task-gemini-38-flash-lite-tts-001 model_id: google/gemini-3.8-flash-lite-tts get_result: method: GET url: >- https://api.modellix.ai/api/v1/tasks/task-gemini-38-flash-lite-tts-001 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: Gemini38FlashLiteTTSRequest: type: object description: >- Use text and voice for single-speaker synthesis, or speakers and turns for two-speaker dialogue. Dialogue requests must omit top-level text, voice, and style. Combined text and trimmed style must not exceed 8,192 Unicode characters. properties: text: type: string description: Verbatim transcript. Required for single-speaker synthesis. minLength: 1 maxLength: 8192 example: Have a wonderful day! style: type: string description: >- Optional delivery direction for single-speaker synthesis. Not spoken aloud. maxLength: 8192 example: cheerful and friendly language_code: type: string description: >- Optional BCP-47 language tag in lowercase. Examples: en-us, cmn-cn, ja-jp. The model can also detect the language from the transcript. pattern: ^[a-z]{2,3}(-[a-z0-9]+)*$ example: en-us voice: type: string description: >- Required for single-speaker synthesis. Prebuilt voice name, extended voice-library ID, or a designed/replicated voice ID (voice_... or voicekey_...). No spaces. minLength: 1 maxLength: 256 example: Kore speakers: type: array description: Exactly two speakers for dialogue. Use with turns. minItems: 2 maxItems: 2 items: $ref: '#/components/schemas/Gemini38FlashLiteTTSSpeaker' turns: type: array description: >- Dialogue turns in order. Each speaker must match a name in speakers, case-sensitively. minItems: 1 items: $ref: '#/components/schemas/Gemini38TTSTurn' AsyncTaskResponse: type: object required: - code - message - data properties: code: type: integer description: Response code, 0 indicates success example: 0 message: type: string description: Response message example: success data: type: object required: - status - task_id - model_id description: >- Task submission details. Poll GET /api/v1/tasks/{task_id} until status is success; audio appears in result.resources with type audio and format wav. properties: status: type: string enum: - pending - processing description: Initial task status example: pending task_id: type: string description: Unique task identifier for polling example: task-gemini-tts-001 model_id: type: string description: Model ID in provider/model format example: google/gemini-3.1-flash-tts get_result: type: object description: Endpoint to query the task result properties: method: type: string example: GET url: type: string example: https://api.modellix.ai/api/v1/tasks/task-gemini-tts-001 Gemini38FlashLiteTTSSpeaker: type: object required: - speaker - voice properties: speaker: type: string description: Speaker name used by turns. Alphanumeric, 1-64 characters. minLength: 1 maxLength: 64 pattern: ^[A-Za-z0-9]+$ example: Joe voice: type: string description: >- Prebuilt voice name or extended voice-library ID, such as Puck or Kore. Designed or replicated voices (voice_... or voicekey_...) are not supported in dialogue. No spaces. minLength: 1 maxLength: 256 example: Puck Gemini38TTSTurn: type: object required: - speaker - text properties: speaker: type: string description: Which configured speaker says this turn. minLength: 1 maxLength: 64 pattern: ^[A-Za-z0-9]+$ example: Joe text: type: string description: Verbatim line for this turn. minLength: 1 maxLength: 8192 example: How is it going today, Jane? style: type: string description: Optional delivery direction for this turn only. Not spoken aloud. maxLength: 8192 example: cheerful and friendly ErrorResponse: type: object required: - code - message properties: code: type: integer description: Error code (equals HTTP status code) example: 400 message: type: string description: 'Error message in format ''Category: detail''' example: 'Invalid parameters: combined prompt and text must be <= 8000 bytes' responses: BadRequest: description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 400 message: 'Invalid parameters: parameter ''text'' is required' Unauthorized: description: Unauthorized - Invalid or missing API Key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 401 message: 'Authentication failed: invalid API key' TooManyRequests: description: Too many requests - Rate limit exceeded headers: X-RateLimit-Limit: description: Maximum requests per minute schema: type: integer example: 100 X-RateLimit-Remaining: description: Remaining quota in current window schema: type: integer example: 0 X-RateLimit-Reset: description: Rate limit window reset time (Unix timestamp) schema: type: integer example: 1704067260 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 429 message: >- Rate limit exceeded: 100 requests per minute, retry after 60 seconds InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 500 message: Internal server error securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Modellix API Key. Format: `Bearer `' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.