Higgs Audio v3 Stt measured on 16 of 81 Speech to text benchmarks16
BenchmarkByScoreRank
No benchmark matches
self-host onlyprice
6.2Open ASR
Mar 2026released
enLanguages
Alternatives?
ModelScoreCostPriceWhat changes
OBetterSpeech v3.1+59%——Languages: not verifiedModelScoreCostPriceWhat changes
Nothing here yet.
ModelScoreCostPriceWhat changes
OSpeech v3.1+59%——Languages: not verifiedrResonant 1 Flash+54%——Languages: not verifiedZZoom Scribe v1+49%——Languages: not verifiedRun it yourself
estimateFits on✓ 8 GB (phone, laptop) · full quality✓ 16 GB · full quality✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
in Speech & VoiceOpen ASR · average WER6.2#20
Open ASR · RTFx109.7#41
Open ASR · URGENT 2024 WER11.9#20
Open ASR · AMI WER7.9#4
Open ASR · VoxPopuli WER5.9#16
FAQ
How much does Higgs Audio v3 Stt cost?›
There is no per-unit API price: self-host only.
Is Higgs Audio v3 Stt free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Higgs Audio v3 Stt, and what is it best at?›
#20 of 61 in Speech to text.
Is Higgs Audio v3 Stt better than Thewhisper Large v3 Turbo?›
On Open ASR · average WER, Higgs Audio v3 Stt scores 6.2 vs 6.1 — about the same.
When was Higgs Audio v3 Stt released? Is there a newer version?›
Released 2026-03-25. It is the current version in its line.
Is Higgs Audio v3 Stt open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Higgs Audio v3 Stt locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
What is Higgs Audio v3 Stt?›
Higgs Audio v3 Stt is an open-weights speech & voice model from Boson AI, released Mar 2026.
What are the best alternatives to Higgs Audio v3 Stt?›
Speech v3.1 (better), Phi 4 Multimodal Instruct (open weights).