> ## Documentation Index > Fetch the complete documentation index at: https://docs.poyo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Gemini 3.8 Flash TTS > Generate native WAV speech from a transcript or a two-speaker dialogue with style guidance. Submission returns a `task_id`. Use [Query Task Status](/api-manual/task-management/status) to track completion, or supply `callback_url` for completion and failure notifications. ## Parameters and combinations Single speaker: supply non-empty `text`, optional `voice` (default `Kore`), and optional `style_instructions`. Dialogue: omit `text` and top-level `voice`; supply exactly two `speakers` with distinct non-empty `speaker_id` values and a `voice` for each. Supply non-empty `turns`; each turn needs a configured `speaker_id`, non-empty `text`, and optional `style_instructions`. Single-speaker and dialogue inputs are mutually exclusive. Global `style_instructions` can be used with either mode. The complete input is limited to 8,192 tokens. `enable_safety_checker` defaults to `true`. Disabling safety checking can require account authorization. Output is native WAV. There are no `output_format`, `temperature`, `language_code`, or `seed` parameters. Voices: `Achernar`, `Achird`, `Algenib`, `Algieba`, `Alnilam`, `Aoede`, `Autonoe`, `Callirrhoe`, `Charon`, `Despina`, `Enceladus`, `Erinome`, `Fenrir`, `Gacrux`, `Iapetus`, `Kore`, `Laomedeia`, `Leda`, `Orus`, `Pulcherrima`, `Puck`, `Rasalgethi`, `Sadachbia`, `Sadaltager`, `Schedar`, `Sulafat`, `Umbriel`, `Vindemiatrix`, `Zephyr`, `Zubenelgenubi`. ## Examples ```json theme={null} { "model": "gemini-3.8-flash-tts", "input": { "text": "Hello! Welcome to PoYo." } } ``` ```json theme={null} { "model": "gemini-3.8-flash-tts", "input": { "speakers": [ { "speaker_id": "host", "voice": "Kore" }, { "speaker_id": "guest", "voice": "Puck" } ], "turns": [ { "speaker_id": "host", "text": "Welcome!" }, { "speaker_id": "guest", "text": "Thank you.", "style_instructions": "Warm and friendly." } ] } } ``` ## Task results The query response uses the common task structure: `task_id`, `status`, `progress`, `files`, and `error_message`. A finished task has `status="finished"`; each result file has `file_url` and `file_type`. Preserve the task ID while polling. Speech appears as `file_type="audio"`; optional timing JSON appears as `file_type="other"`. ## OpenAPI ````yaml api-manual/music-series/gemini-3-8-flash-tts.json POST /api/generate/submit openapi: 3.1.0 info: title: PoYo AI - Gemini 3.8 Flash TTS API description: >- Generate native WAV speech from a transcript or a two-speaker dialogue with style guidance. version: 1.0.0 servers: - url: https://api.poyo.ai security: - BearerAuth: [] paths: /api/generate/submit: post: tags: - Gemini 3.8 Flash TTS summary: Submit Gemini 3.8 Flash TTS Task description: >- Generate native WAV speech from a transcript or a two-speaker dialogue with style guidance. operationId: submit_gemini_3_8_flash_tts requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/SubmitRequest' examples: example-1: value: model: gemini-3.8-flash-tts input: text: Hello! Welcome to PoYo. example-2: value: model: gemini-3.8-flash-tts input: speakers: - speaker_id: host voice: Kore - speaker_id: guest voice: Puck turns: - speaker_id: host text: Welcome! - speaker_id: guest text: Thank you. style_instructions: Warm and friendly. responses: '200': description: Task accepted; query the task for final files. content: application/json: schema: $ref: '#/components/schemas/SubmitResponse' components: schemas: SubmitRequest: type: object required: - model - input properties: model: type: string enum: - gemini-3.8-flash-tts input: $ref: '#/components/schemas/ModelInput' callback_url: type: string format: uri description: Optional completion or failure callback URL. SubmitResponse: type: object required: - code - data properties: code: type: integer example: 200 data: type: object required: - task_id - status - created_time properties: task_id: type: string example: task-unified-1757165031-uyujaw3d status: type: string enum: - not_started example: not_started created_time: type: string format: date-time example: '2026-10-13T10:30:00+08:00' ModelInput: type: object additionalProperties: false properties: voice: enum: - Achernar - Achird - Algenib - Algieba - Alnilam - Aoede - Autonoe - Callirrhoe - Charon - Despina - Enceladus - Erinome - Fenrir - Gacrux - Iapetus - Kore - Laomedeia - Leda - Orus - Pulcherrima - Puck - Rasalgethi - Sadachbia - Sadaltager - Schedar - Sulafat - Umbriel - Vindemiatrix - Zephyr - Zubenelgenubi type: string default: Kore description: >- Single-speaker voice, default Kore. Omit when using speakers and turns. speakers: type: array minItems: 2 maxItems: 2 items: required: - speaker_id - voice additionalProperties: false type: object properties: voice: enum: - Achernar - Achird - Algenib - Algieba - Alnilam - Aoede - Autonoe - Callirrhoe - Charon - Despina - Enceladus - Erinome - Fenrir - Gacrux - Iapetus - Kore - Laomedeia - Leda - Orus - Pulcherrima - Puck - Rasalgethi - Sadachbia - Sadaltager - Schedar - Sulafat - Umbriel - Vindemiatrix - Zephyr - Zubenelgenubi type: string speaker_id: type: string minLength: 1 pattern: \S description: >- Required together with turns for dialogue. Exactly two speakers with distinct non-empty speaker_id values. Omit text and top-level voice. turns: type: array minItems: 1 items: required: - speaker_id - text additionalProperties: false type: object properties: speaker_id: type: string minLength: 1 pattern: \S text: type: string minLength: 1 pattern: \S style_instructions: type: string description: >- Required together with speakers for dialogue. At least one turn; speaker_id must reference a configured speaker. Each turn supports optional style_instructions. enable_safety_checker: type: boolean default: true description: >- Enable input safety checking. Disabling requires account authorization when applicable. style_instructions: type: string description: Global delivery style, separate from the transcript. text: type: string minLength: 1 pattern: \S description: >- Single-speaker transcript. Required for single-speaker mode. Omit when using speakers and turns. Complete input is limited to 8192 tokens. description: >- Use either text (single speaker) or speakers with turns (dialogue). These modes are mutually exclusive; dialogue cannot include top-level text or voice. securitySchemes: BearerAuth: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.