Model Cadence
Plus $4/mo

Chirp 3

Google · Released Aug 29, 2025 · Closed weights

Multilingual speech-to-text model with diarization and automatic language detection

Open in the timeline
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 29, 2025
WEIGHTSClosed weights
CONTEXT WINDOWNot listed
MAX OUTPUT0
REASONINGNot listed
TOOL CALLINGNot listed
INPUTSaudio/wav, audio/mpeg, audio/flac, audio/mp4, audio/ogg, audio/webm, audio/aac
OUTPUTStext

Models.dev record ↗

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.