whatmodel.sh / stt / Chirp

Chirp

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Chirp is a closed-weights speech-to-text model from Google, released May 2023. Licence: proprietary.

Catalogue identity notes

Original Google Cloud Speech-to-Text model 'chirp' (USM-based first generation; leaderboard entry google/chirp). Distinct from chirp_2 and chirp_3. The current STT v2 transcription-model list (observed 2026-09-28) names only chirp_3, chirp_2 and telephony, so api is null.

Model information sources

Release date ↗

50.1±3.7comparison only: no current run option verifiedfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of Chirp, out of 176 with a score, then more from Google.

#modelscorewhereRAMreleased
108Moonshine Streaming Medium Useful Sensors (Moonshine AI)50±3local~1.8GB2026-01
109VibeVoice-ASR-BitNet Microsoft50±4local~1.7GB2026-07
110Chirp Google50±4comparison only2023-05
111Parakeet TDT-CTC 110M NVIDIA50±3local~1.1GB2024-09
112ESPnet HuBERT Large + Conformer + Transformer LM ESPnet50±4local~8GB2022-01
more from Google
11Gemini 3.5 Transcribe Google67±6api $0.0050/audio min2026-08
31Chirp 3 Google61±2api price unknown2025-03
33Gemini 3.5 Transcribe Live Google61±3api $0.0090/audio min2026-08

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

long-form transcription▁▁▅▁·▃▅█▆▁▂▂ #24 of 31 * · 47% of its score · 1 test

Trails Whisper large (v1) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Open ASR English long-form WER11.5% ✎▁▁▅▁·▃▅█▆▁▂▂ beats 7/30avg 12%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%typical
other tests1 not in a task · 47% of its score
testresultvs the others in its rundifficultycountswhy
Open ASR English short-form WER (March 2026)8.3% ✎▁▁▁▃··▁▁▂██▆ beats 30/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47%blunt

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · Open ASR Leaderboard 95%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Open ASR Leaderboard2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%Apache-2.0
prior · pull toward the middle▇▇ 5%
weighted average= 50.1

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json