{"data":{"id":"google/gemini-3.5-transcribe","name":"Google: Gemini 3.5 Transcribe","created":1790295820,"description":"Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers. Audio...","architecture":{"tokenizer":"Gemini","instruct_type":null,"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"]},"endpoints":[{"name":"Google AI Studio | google/gemini-3.5-transcribe-20260827","model_id":"google/gemini-3.5-transcribe","model_name":"Google: Gemini 3.5 Transcribe","context_length":98304,"pricing":{"prompt":"0.000002","completion":"0.000012","discount":0},"provider_name":"Google AI Studio","tag":"google-ai-studio","service_tier":null,"quantization":"unknown","max_completion_tokens":32768,"max_prompt_tokens":null,"supported_parameters":[],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":null,"uptime_last_1d":100,"supports_implicit_caching":false,"native_tools":{},"supports_voice_cloning":false,"supports_multiple_audio_references":false,"supports_image_reference":false,"supports_diarization":false,"latency_last_30m":null,"throughput_last_30m":null}]}}