Transcribe with Vosk
12.0%
WER
20
Languages
100.0x
Speed
Apache 2.0
License
About Vosk
Vosk is an offline speech recognition toolkit that works without an internet connection. It supports 20+ languages with compact models that can run on mobile devices, Raspberry Pi, and any platform. Built on Kaldi and Zipformer architectures.
Languages Supported by Vosk
Model Info
- ProviderAlpha Cephei
- Architecture-
- LicenseApache 2.0
- UpdatedMar 2026
Frequently Asked Questions
Vosk is a speech-to-text model by Alpha Cephei. STT.ai hosts Vosk on our GPU infrastructure so you can use it without provisioning your own hardware — upload audio or video and pick Vosk from the model picker.
On standard benchmarks, Vosk achieves around 12.0% Word Error Rate. Real-world accuracy depends on audio quality, accent, and language; for noisy or accented recordings, expect a few percentage points higher WER.
Vosk runs on STT.ai's free tier — every visitor gets 600 minutes/month at no cost. Paid plans add longer per-file limits, private transcripts, and priority queueing.
Vosk is released under Apache 2.0, a permissive open-source license. You can self-host Vosk on your own hardware or use our hosted version — both are commercially usable.
Vosk supports 20 languages. Auto-detection picks the right language for most audio; you can also specify it manually for a small accuracy lift.
Vosk processes audio at about 100.0x real-time on our GPUs. A 1-hour audio file finishes in under 1 minutes; longer files queue and notify by email when done.
Vosk has 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 accepts every format STT.ai supports — MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, and others. Output as TXT, SRT, VTT, DOCX, JSON, or PDF.
Yes. Speaker diarization runs alongside Vosk for every transcription — each speaker is labeled and you can rename them in the editor afterwards.
Yes. 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.
Use the compare-stt tool to run Vosk against any other supported model on the same audio — you'll see WER, segment count, speaker labels, and confidence scores side-by-side. The Vosk vs Whisper Large V3 comparison is the most commonly run.
Yes. Specify "vosk" as the model parameter on the /v1/transcribe endpoint. Python and Node.js SDKs include Vosk examples. Free API tier includes 100 minutes/month.
Yes. Because Vosk is Apache 2.0-licensed, you can self-host it. STT.ai's open-source page lists the project repo and weights. Most production teams use our hosted version to skip GPU procurement, model swaps, and ops.