{"models":[{"id":"gemini/gemini-3.5-transcribe","type":"stt","name":"Gemini 3.5 Transcribe","model_id":"gemini-3.5-transcribe","capabilities":["speech_to_text","diarization"],"speed":"fast","quality":"best","context_window":0,"description":"Google's speech-to-text model with automatic language detection across 85+ languages, speaker diarization, word-level timestamps and custom vocabulary biasing.","params":{"stt":{"formats":["mp3","wav","aiff","aac","ogg","flac"],"diarize":true}},"pricing":{"billing_unit":"per_minute","rates":[{"unit":"per_minute","amount":0.0051}],"price_per_minute":0.0051},"region":"US","model":"gemini-3.5-transcribe","family":"gemini-3.5-transcribe","pooled":true,"provider":{"slug":"google","display_name":"Google","owner_country":"US"},"service_route":{"id":"gemini-direct/api-us","adapter":"gemini"},"maker":{"slug":"google","display_name":"Google","country":"US"},"compliance":{"residency":"US","country":"United States","inference_location":"US","storage_location":"GLOBAL","zdr":{"logging":true,"moderation":true,"caching":null,"training":false,"subprocessors":null},"training":"no","logging":"abuse_monitoring","moderation":"default_on","caching":"unknown","content_storage":"retained","dpa_available":true,"third_party_access":true,"transfer_mechanism":"sccs","route_id":"gemini-direct/api-us"},"release":{"date":"2026-08-26","source":"vendor","url":"https://ai.google.dev/gemini-api/docs/changelog#08-26-2026"},"references":[{"kind":"model_card","url":"https://ai.google.dev/gemini-api/docs/models/gemini-3.5-transcribe","created_at":"2026-10-07T08:08:27.555553Z","updated_at":"2026-10-07T08:08:27.555553Z"},{"kind":"model_card","url":"https://deepmind.google/models/model-cards/gemini-3-5-audio/","created_at":"2026-10-07T08:08:27.555553Z","updated_at":"2026-10-07T08:08:27.555553Z"}],"input_modalities":["text","audio"],"output_modalities":["transcription"]},{"id":"gemini/gemini-3.5-transcribe-live","type":"realtime","name":"Gemini 3.5 Transcribe Live","model_id":"gemini-3.5-transcribe-live","capabilities":["speech_to_text","streaming","audio","text","vad"],"speed":"fast","cost":0.436,"quality":"best","context_window":0,"description":"Google's low-latency streaming speech-to-text over the Gemini Live API (BidiGenerateContent). Automatic language detection with mid-session code-switching; no diarization or word timestamps.","params":{},"pricing":{"billing_unit":"per_mtok","input":[3.5],"output":[21],"audio_input":[3.5],"audio_output":[21]},"region":"US","model":"gemini-3.5-transcribe-live","family":"gemini-3.5-transcribe-live","pooled":true,"provider":{"slug":"google","display_name":"Google","owner_country":"US"},"service_route":{"id":"gemini-direct/api-us","adapter":"gemini"},"maker":{"slug":"google","display_name":"Google","country":"US"},"compliance":{"residency":"US","country":"United States","inference_location":"US","storage_location":"GLOBAL","zdr":{"logging":true,"moderation":true,"caching":null,"training":false,"subprocessors":null},"training":"no","logging":"abuse_monitoring","moderation":"default_on","caching":"unknown","content_storage":"retained","dpa_available":true,"third_party_access":true,"transfer_mechanism":"sccs","route_id":"gemini-direct/api-us"},"release":{"date":"2026-08-26","source":"vendor","url":"https://ai.google.dev/gemini-api/docs/changelog#08-26-2026"},"references":[{"kind":"model_card","url":"https://ai.google.dev/gemini-api/docs/models/gemini-3.5-transcribe","created_at":"2026-10-07T08:08:27.555553Z","updated_at":"2026-10-07T08:08:27.555553Z"},{"kind":"model_card","url":"https://deepmind.google/models/model-cards/gemini-3-5-audio/","created_at":"2026-10-07T08:08:27.555553Z","updated_at":"2026-10-07T08:08:27.555553Z"}],"input_modalities":["text","audio"],"output_modalities":["transcription"]}],"total":2,"offset":0,"limit":50}