Gemini 3.5 Transcribe
Speech-to-text model with language detection, speaker diarization, word timestamps, and custom vocabulary
- Price per 1M tokens
- $2 / $12 input / output · Google
- Context window
- 98.3K tokens in · 32.8K out
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
Google's past year
38 release days in the past year, about one every 10 days. The next is expected around Oct 31, 2026. Forecasts ↗
NovDecJanFebMarAprMayJunJulAugSepOct
Specifications
RELEASE DATEAug 26, 2026
WEIGHTSClosed weights
CONTEXT WINDOW98.3K
MAX OUTPUT32.8K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTSaudio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac, audio/mpeg, audio/m4a, audio/l16, audio/opus, audio/alaw, audio/mulaw, audio/webm
OUTPUTStext
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.