{"servers":[{"url":"https://api.modellix.ai/api/v1/google/gemini-3.5-transcribe"}],"post":{"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":{"content":{"application/json":{"examples":{"basic":{"summary":"Minimal request","value":{"audio":"https://cdn.example.com/meeting.wav"}},"smart":{"summary":"Smart formatting without timestamps","value":{"audio":"https://cdn.example.com/meeting.wav","mode":"smart"}},"verbatim_full":{"summary":"Language hints, vocabulary, diarization, and word timestamps","value":{"audio":"https://cdn.example.com/meeting.wav","custom_vocabulary":["oatmilk","Modellix"],"diarization":true,"language_codes":["en-US"],"word_timestamp":true}}},"schema":{"additionalProperties":false,"properties":{"audio":{"description":"Public HTTPS URL of the audio file. Maximum duration 15 minutes; maximum size 300 MB. Common formats include WAV, MP3, and FLAC.","minLength":1,"pattern":"^https://","type":"string"},"custom_vocabulary":{"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.","items":{"minLength":1,"type":"string"},"maxItems":1000,"type":"array"},"diarization":{"description":"When true, label speakers (up to 8). Cannot be combined with mode=smart. Attribution for three or more speakers is experimental.","type":"boolean"},"language_codes":{"description":"Optional language hints. Omit for automatic detection. Simplified Chinese is cmn-Hans-CN.","items":{"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"],"type":"string"},"type":"array"},"mode":{"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.","enum":["verbatim","smart"],"type":"string"},"word_timestamp":{"description":"When true, include word-level timestamps. Cannot be combined with mode=smart.","type":"boolean"}},"required":["audio"],"type":"object"}}},"required":true},"responses":{"200":{"content":{"application/json":{"example":{"code":0,"data":{"get_result":{"method":"GET","url":"https://api.modellix.ai/api/v1/tasks/task-gemini-transcribe-001"},"model_id":"google/gemini-3.5-transcribe","status":"pending","task_id":"task-gemini-transcribe-001"},"message":"success"},"schema":{"properties":{"code":{"description":"Response code, 0 indicates success","example":0,"type":"integer"},"data":{"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":{"get_result":{"description":"Endpoint to query the task result","properties":{"method":{"example":"GET","type":"string"},"url":{"example":"https://api.modellix.ai/api/v1/tasks/task-gemini-transcribe-001","type":"string"}},"type":"object"},"model_id":{"description":"Model ID in provider/model format","example":"google/gemini-3.5-transcribe","type":"string"},"status":{"description":"Initial task status","enum":["pending","processing"],"example":"pending","type":"string"},"task_id":{"description":"Unique task identifier for polling","example":"task-gemini-transcribe-001","type":"string"}},"required":["status","task_id","model_id"],"type":"object"},"message":{"description":"Response message","example":"success","type":"string"}},"required":["code","message","data"],"type":"object"}}},"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."},"400":{"content":{"application/json":{"example":{"code":400,"message":"Invalid parameters: parameter 'audio' is required"},"schema":{"properties":{"code":{"description":"Error code (equals HTTP status code)","example":400,"type":"integer"},"message":{"description":"Error message in format 'Category: detail'","example":"Invalid parameters: audio is required","type":"string"}},"required":["code","message"],"type":"object"}}},"description":"Invalid request parameters"},"401":{"content":{"application/json":{"example":{"code":401,"message":"Authentication failed: invalid API key"},"schema":{"properties":{"code":{"description":"Error code (equals HTTP status code)","example":400,"type":"integer"},"message":{"description":"Error message in format 'Category: detail'","example":"Invalid parameters: audio is required","type":"string"}},"required":["code","message"],"type":"object"}}},"description":"Unauthorized - Invalid or missing API Key"},"429":{"content":{"application/json":{"example":{"code":429,"message":"Rate limit exceeded: 100 requests per minute, retry after 60 seconds"},"schema":{"properties":{"code":{"description":"Error code (equals HTTP status code)","example":400,"type":"integer"},"message":{"description":"Error message in format 'Category: detail'","example":"Invalid parameters: audio is required","type":"string"}},"required":["code","message"],"type":"object"}}},"description":"Too many requests - Rate limit exceeded","headers":{"X-RateLimit-Limit":{"description":"Maximum requests per minute","schema":{"example":100,"type":"integer"}},"X-RateLimit-Remaining":{"description":"Remaining quota in current window","schema":{"example":0,"type":"integer"}},"X-RateLimit-Reset":{"description":"Rate limit window reset time (Unix timestamp)","schema":{"example":1704067260,"type":"integer"}}}},"500":{"content":{"application/json":{"example":{"code":500,"message":"Internal server error"},"schema":{"properties":{"code":{"description":"Error code (equals HTTP status code)","example":400,"type":"integer"},"message":{"description":"Error message in format 'Category: detail'","example":"Invalid parameters: audio is required","type":"string"}},"required":["code","message"],"type":"object"}}},"description":"Internal server error"}},"summary":"Gemini 3.5 Transcribe","x-mint":{"href":"google/gemini-3-5-transcribe"}}}