Transcribe with Vosk
12.0%
WER
20
Languages
100.0x
Speed
Apache 2.0
License
About Vosk
Languages Supported by Vosk
Model Info
- ProviderAlpha Cephei
- Architecture-
- LicenseApache 2.0
- UpdatedMar 2026
Zvimwe zvinobvunzwa kakawanda
Vosk imhando yemutauro-ku-mutauro yakagadzirwa ne Alpha Cephei. STT.ai inochengeta Vosk pane yedu GPU infrastructure kuitira kuti iwe ugone kuishandisa pasina kuisa yako hardware. Upload audio kana video uye sarudza Vosk kubva kumodeli picker.
Real-world kunyatsonzwisisa kunoenderana nemhando yezwi, accent, uye rurimi; For noisy kana accented rekodhi, kutarisira zvishoma zvidimbu zviviri zvemazana yepamusoro WER.
Vosk inofamba pa STT.ai yemahara tier - chero muenzi anowana 600 maminitsi / mwedzi pasina mutengo. Yakabhadharwa mishandirapamwe inowedzera zvishoma zvishoma zvishoma, zvemukati zvemukati, uye priority queueing.
Vosk inoburitswa pasi peApache 2.0, iyo yakavhurika-chigadzirwa chigadzirwa chitupa. Iwe unogona kuisa Vosk pane yako hardware kana kushandisa yedu inochengetwa vhezheni. Imwe neimwe inoshandiswa mukutengesa.
Vosk inotsigira 20 mazita ezvinyorwa. Kuwana otomatiki kunosarudza zvirinani zita rezvinyorwa zvemavhidhiyo; unogonawo kuisarudza nemunhu kuti uwane kunyatsoita kwakanaka.
Vosk inogadzirisa audio pazvinosvika 100.0x real-time pane edu GPUs. 1-hour audio file inosvika pasi pe 1 maminitsi; zvinopfuura zvinyorwa zvinomirira uye zvinozivisa neemail kana zvaitwa.
Vosk ine 50M parameters. Larger models tend to be more accurate but slower; STT.ai hosts Vosk on GPU so the parameter count doesn't affect your client-side performance.
Vosk inogamuchira ese mafomati STT.ai anotsigira - MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, uye vamwe.Kuburitsa se TXT, SRT, VTT, DOCX, JSON, kana PDF.
Yega. Mutauro diarization inofamba pamwe Vosk yese transcription — mumwe mutauro iri rakanyorwa uye unogona kuchinja zita ravo mu editor mushure.
Yeah. Vosk runs in our managed environment — audio is processed and deleted by default and never used for training without explicit opt-in. Pro plans add client-side encryption for transcripts at rest.
Usati washandisa Vosk, shandisawo Vosk vs Whisper Large V3 kuongorora kuti uone kuti Vosk inoenderana nemhando ipi neipi yefoni. Unogona kuona WER, segment count, speaker labels, uye confidence scores side-by-side. Vosk vs Whisper Large V3 kuongorora ndiyo inonyanya kushandiswa.
Yeah. Chidza "vosk" separameter yemufananidzo pa /v1/transcribe endpoint. Python uye Node.js SDKs dzinosanganisira Vosk mifananidzo. Yemahara API tier inosanganisira 100 maminitsi / mwedzi.
Yeah. Nekudaro, nekuti Vosk ine Apache 2.0-lisensi, unogona kuichengeta iwe pachako. STT.ai's open-source peji rinonyora repo uye zviyero zveprojekiti. Zvikwata zvakawanda zvekugadzira zvinoshandisa yedu inochengetwa vhezheni kuti urege kubhadharisa GPU, kuchinja mamodheru, uye ops.