> ## 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 3.5 Transcribe > [Core Function] Gemini 3.5 Transcribe is Google's speech-to-text model for complete pre-recorded audio. [Strengths] Accurate multilingual recognition across 85+ languages with optional language hints, custom vocabulary for brand names, speaker labels (up to 8 speakers), word-level timestamps, and Smart formatting that cleans punctuation and numbers. [Best For] Meeting notes, captions and subtitles, multilingual recordings, call logs, and speaker-attributed transcripts. [Limitations] Do NOT use this if the audio is not a public HTTPS URL, longer than 15 minutes, or larger than 300 MB. Do NOT use file upload. Do NOT combine mode=smart with word timestamps or speaker labels. This endpoint does not support live or streaming transcription. [Routing] Choose this model for Google Gemini file transcription with speaker labels or Smart formatting. For Microsoft recognition use MAI-Transcribe; for OpenAI formats such as SRT or VTT use Whisper. ## OpenAPI ````yaml /media-model-api/google/google-s2t.json post /google/gemini-3.5-transcribe openapi: 3.1.0 info: title: Google Speech-to-Text Models API description: >- Google Gemini 3.5 Transcribe speech-to-text. Submit a public HTTPS audio URL as an async task; poll GET /api/v1/tasks/{task_id} for the transcription result. version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai servers: - url: https://api.modellix.ai/api/v1 description: Google Gemini speech-to-text models API security: - bearerAuth: [] paths: /google/gemini-3.5-transcribe: post: summary: Gemini 3.5 Transcribe description: >- [Core Function] Gemini 3.5 Transcribe is Google's speech-to-text model for complete pre-recorded audio. [Strengths] Accurate multilingual recognition across 85+ languages with optional language hints, custom vocabulary for brand names, speaker labels (up to 8 speakers), word-level timestamps, and Smart formatting that cleans punctuation and numbers. [Best For] Meeting notes, captions and subtitles, multilingual recordings, call logs, and speaker-attributed transcripts. [Limitations] Do NOT use this if the audio is not a public HTTPS URL, longer than 15 minutes, or larger than 300 MB. Do NOT use file upload. Do NOT combine mode=smart with word timestamps or speaker labels. This endpoint does not support live or streaming transcription. [Routing] Choose this model for Google Gemini file transcription with speaker labels or Smart formatting. For Microsoft recognition use MAI-Transcribe; for OpenAI formats such as SRT or VTT use Whisper. operationId: gemini35Transcribe requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Gemini35TranscribeRequest' examples: basic: summary: Minimal request value: audio: https://cdn.example.com/meeting.wav verbatim_full: summary: Language hints, vocabulary, diarization, and word timestamps value: audio: https://cdn.example.com/meeting.wav language_codes: - en-US custom_vocabulary: - oatmilk - Modellix diarization: true word_timestamp: true smart: summary: Smart formatting without timestamps value: audio: https://cdn.example.com/meeting.wav mode: smart responses: '200': description: >- Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; the transcription appears in result.resources. See Common API: Query Task Result and STT Result Schema. content: application/json: schema: $ref: '#/components/schemas/AsyncTaskResponse' example: code: 0 message: success data: status: pending task_id: task-gemini-transcribe-001 model_id: google/gemini-3.5-transcribe get_result: method: GET url: >- https://api.modellix.ai/api/v1/tasks/task-gemini-transcribe-001 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: Gemini35TranscribeRequest: type: object required: - audio additionalProperties: false properties: audio: type: string minLength: 1 pattern: ^https:// description: >- Public HTTPS URL of the audio file. Maximum duration 15 minutes; maximum size 300 MB. Common formats include WAV, MP3, and FLAC. language_codes: type: array items: type: string enum: - af-ZA - am-ET - ar-EG - hy-AM - as-IN - az-AZ - be-BY - bn-BD - bn-IN - bs-BA - bg-BG - rup-BG - my-MM - yue-Hant-HK - ca-ES - ceb - km-KH - hr-HR - cs-CZ - da-DK - nl-NL - en-AU - en-GB - en-IN - en-US - et-EE - fa-IR - fil-PH - fi-FI - fr-FR - fr-CA - gl-ES - ka-GE - de-DE - el-GR - gu-IN - ha-NG - he-IL - hi-IN - hu-HU - is-IS - id-ID - it-IT - ja-JP - jv-ID - kea-CV - kn-IN - kk-KZ - ko-KR - ky-KG - lv-LV - ln-CD - lt-LT - mk-MK - ms-MY - ml-IN - mt-MT - cmn-Hans-CN - mr-IN - mn-MN - ne-NP - nb-NO - or-IN - pl-PL - pt-BR - pt-PT - pa-IN - pa-Guru-IN - ro-RO - ru-RU - sr-RS - sd-Arab-IN - sk-SK - sl-SI - es-419 - es-ES - es-US - sw-KE - sv-SE - tg-TJ - te-IN - th-TH - tr-TR - uk-UA - uz-UZ - vi-VN description: >- Optional language hints. Omit for automatic detection. Simplified Chinese is cmn-Hans-CN. custom_vocabulary: type: array maxItems: 1000 items: type: string minLength: 1 description: >- Optional terms that bias recognition, such as brand names and proper nouns. Up to 1000 items. Works best when language_codes is also set. diarization: type: boolean description: >- When true, label speakers (up to 8). Cannot be combined with mode=smart. Attribution for three or more speakers is experimental. word_timestamp: type: boolean description: >- When true, include word-level timestamps. Cannot be combined with mode=smart. mode: type: string enum: - verbatim - smart default: verbatim description: >- verbatim keeps speech as spoken, including filler words. smart applies dictation-style formatting such as punctuation and numbers. smart cannot be used with word_timestamp or diarization. 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; the transcription appears in result.resources. See Common API: Query Task Result and STT Result Schema. 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-transcribe-001 model_id: type: string description: Model ID in provider/model format example: google/gemini-3.5-transcribe 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-transcribe-001 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: audio is required' responses: BadRequest: description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 400 message: 'Invalid parameters: parameter ''audio'' 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 ````