> ## Documentation Index > Fetch the complete documentation index at: https://docs.vidgo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Gemini 3.8 Flash Lite TTS > The Gemini 3.8 Flash-Lite TTS API generates WAV speech at scale from a single voice or two-speaker dialogue, with 30 preset voices and style instructions. > [!TIP] > > 1. After submission, a `task_id` will be returned. If you provided a `callback_url`, when the task status becomes `finished` or `failed`, a POST request will be sent to the `callback_url`. > 2. Regardless of whether `callback_url` is provided, you can retrieve the result through the unified [Query Task Status](https://docs.vidgo.ai/api-manual/task-management/status.md) endpoint. Gemini 3.8 Flash-Lite TTS is Google's high-throughput text-to-speech model. It turns text, or a scripted conversation between two speakers, into WAV audio with 30 preset voices, auto-detects the language (Google lists 101) and takes plain-language style instructions. Use it for read-aloud features, notifications, voice-agent prompts and other high-volume, everyday speech. Gemini 3.8 Flash-Lite TTS takes the same request fields as [Gemini 3.8 Flash TTS](https://docs.vidgo.ai/api-manual/music-series/google-gemini-3-8-flash-text-to-speech.md), which Google positions for maximum voice fidelity and complex dialogue. Switch between them by changing `model`. ## Models * **google/gemini-3.8-flash-lite/text-to-speech** — Gemini 3.8 Flash-Lite text-to-speech for high-volume single-voice or two-speaker audio. ## Features * Text-to-speech with one voice, or a scripted dialogue between two speakers. * 30 preset voices, set per request or per speaker. * Plain-language `style_instructions` for tone, pace, accent and emotion, globally or per dialogue turn. * Automatic language detection (Google lists 101 languages). * WAV audio output. ## Input modes * **Single speaker**: send `text` and, optionally, `voice` (default `Kore`). * **Two-speaker dialogue**: send exactly two `speakers` and a list of `turns`. Do not send top-level `text` or `voice` in this mode. ## Required parameters Single speaker: * `text` (string): The text to speak. Not blank. Two-speaker dialogue: * `speakers` (object\[]): Exactly two objects, each with only: * `speaker_id` (string): A non-empty alias, unique within the request, such as `host`. * `voice` (string): One of the [Voice Presets](#voice-presets). * `turns` (object\[]): At least one line, in speaking order: * `speaker_id` (string): Must match one of the two `speakers`. * `text` (string): What that speaker says. Not blank. * `style_instructions` (string, optional): Direction for this line only. ## Optional parameters * `voice` (string): Single-speaker mode only. One of the [Voice Presets](#voice-presets). Default `Kore`. * `style_instructions` (string): Global direction for the whole request, such as `Calm, warm documentary narration`. Works in both modes. * `enable_safety_checker` (boolean): Run the upstream safety checker. Default `true`. ## Output The finished task returns one WAV audio file in the `files` array of [Query Task Status](https://docs.vidgo.ai/api-manual/task-management/status.md) and the callback payload. The output format is fixed; there is no `output_format` field. ## Voice Presets `voice` and `speakers[].voice` accept these 30 values (case-sensitive): > [accordion] Supported voice values > > * `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 * **Single-speaker read-aloud**: a message summary read with `voice: Puck`. * **Two-speaker support dialogue**: `agent` (`Kore`) and `caller` (`Charon`) with a global `style_instructions`, plus a `callback_url`. ## Notes * Credits are reserved at submission and depend on the billable character count: `text`, the global `style_instructions`, and every turn's `text` and `style_instructions`. Speaker IDs are not counted. A failed task is refunded in full. See the [pricing page](https://vidgo.ai/apis/api-pricing) for current rates. * Flash-Lite is billed at a lower rate than [Gemini 3.8 Flash TTS](https://docs.vidgo.ai/api-manual/music-series/google-gemini-3-8-flash-text-to-speech.md). * Dialogue supports exactly two speakers. A third speaker, a `speaker_id` in `turns` that is not in `speakers`, or top-level `text`/`voice` in a dialogue request returns 400. * Put delivery directions in `style_instructions`, not in `text`; the model may read directions inside `text` aloud. * `output_format`, `language_code`, `temperature`, `seed` and timestamps are not supported on this endpoint, and neither are voice cloning or custom voices. ## OpenAPI ````yaml api-manual/music-series/google-gemini-3-8-flash-lite-text-to-speech.json POST /api/generate/submit openapi: 3.0.0 info: title: Vidgo API - Gemini 3.8 Flash Lite TTS description: >- The Gemini 3.8 Flash-Lite TTS API generates WAV speech at scale from a single voice or two-speaker dialogue, with 30 preset voices and style instructions. version: 1.0.0 servers: - url: https://api.vidgo.ai description: Production server security: - BearerAuth: [] paths: /api/generate/submit: post: tags: - Audio Series summary: Gemini 3.8 Flash Lite TTS description: >- Send `text` (plus optional `voice`) for one speaker, or `speakers` + `turns` for a two-speaker dialogue; dialogue requests must not include top-level `text` or `voice`. Any field not listed, such as `output_format`, `language_code` or `temperature`, returns 400. operationId: submit_google_gemini_3_8_flash_lite_text_to_speech requestBody: required: true content: application/json: schema: type: object required: - model - input properties: model: type: string description: Model ID. Use `google/gemini-3.8-flash-lite/text-to-speech`. example: google/gemini-3.8-flash-lite/text-to-speech callback_url: type: string format: uri nullable: true description: >- Optional public HTTP(S) endpoint that receives a POST when the task becomes `finished` or `failed`. HTTPS is recommended. Omit it, or send `null` or an empty string, to disable callbacks. example: https://your-domain.com/callback input: type: object properties: text: type: string minLength: 1 example: Welcome to the city museum. The east wing opens at ten. description: >- Single speaker: the text to speak. Required in single-speaker mode, not blank. Must be omitted in dialogue mode. voice: type: string 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 default: Kore description: >- Single speaker: preset voice. Must be omitted in dialogue mode. speakers: type: array items: type: object required: - speaker_id - voice properties: speaker_id: type: string minLength: 1 example: host description: >- Speaker alias referenced by `turns`. Non-empty and unique. voice: type: string 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 description: Preset voice for this speaker. additionalProperties: false description: One speaker. minItems: 2 maxItems: 2 description: >- Dialogue: exactly two speakers. Each object has only `speaker_id` and `voice`. turns: type: array items: type: object required: - speaker_id - text properties: speaker_id: type: string example: host description: Must match a `speaker_id` in `speakers`. text: type: string minLength: 1 description: What the speaker says. Not blank. style_instructions: type: string description: >- Optional delivery direction for this line only, such as `laughing` or `whispering`. additionalProperties: false description: One line of dialogue. minItems: 1 description: >- Dialogue: the lines in speaking order. At least one turn. style_instructions: type: string description: >- Optional global direction for tone, pace, accent or emotion, such as `Calm, warm documentary narration`. Applies in both modes. enable_safety_checker: type: boolean default: true description: Run the upstream safety checker. additionalProperties: false description: >- Generation parameters. Send `text` (single speaker) or `speakers` + `turns` (two-speaker dialogue), not both. examples: single_speaker: summary: Single-speaker read-aloud value: model: google/gemini-3.8-flash-lite/text-to-speech input: text: >- You have three new messages. The first is from Dana: running ten minutes late, save me a seat. voice: Puck dialogue: summary: Two-speaker support dialogue value: model: google/gemini-3.8-flash-lite/text-to-speech callback_url: https://your-domain.com/callback input: speakers: - speaker_id: agent voice: Kore - speaker_id: caller voice: Charon turns: - speaker_id: caller text: Hi, my router keeps dropping the connection. - speaker_id: agent text: >- Sorry about that. Let's restart it together, it only takes a minute. style_instructions: Friendly, clear customer-support tone responses: '200': description: Task submitted content: application/json: schema: type: object required: - code - data properties: code: type: integer enum: - 200 description: HTTP status code. data: type: object required: - task_id - status - created_time properties: task_id: type: string description: >- Task ID. Use it with [Query Task Status](/api-manual/task-management/status). status: type: string enum: - not_started description: Initial task status. created_time: type: string format: date-time description: Time the task was created (ISO 8601). example: code: 200 data: task_id: task-unified-1762160000-abc123 status: not_started created_time: '2026-11-03T10:30:00' '400': description: >- Invalid input, unsupported field, inaccessible media, or insufficient credits content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '401': description: Invalid credentials content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '403': description: Access denied content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '404': description: Unknown or disabled model content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '408': description: Request timed out content: text/plain: schema: type: string example: Request timeout '422': description: Invalid JSON or non-object request body content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '429': description: Rate or API key credit limit exceeded content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '500': description: Internal error content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '502': description: Unable to create the upstream generation task content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. '503': description: The requested model is temporarily unavailable content: application/json: schema: type: object required: - detail properties: detail: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} description: Error message. components: securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key description: >- All API endpoints require Bearer Token authentication Get your API Key: Go to **Dashboard → API Key** ([API Key Management Page](https://vidgo.ai/apis/dashboard/api-key)) to get your API Key Add it to the request header: ``` Authorization: Bearer VIDGO_API_KEY ``` ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.