Vosk
7.6#17 in ai transcription toolsFree planFree planAndroidiOSAPILinux
VisitVosk vs Whisper
What both publish
| Fact | Vosk | Whisper |
|---|---|---|
| Export formats | TXT,SRT | txt,vtt,srt,tsv,json,jsonl |
| Intended users | The FAQ describes Vosk as a practical, plug-and-play speech recognition library for applications, while suggesting Kaldi for research. | OpenAI describes the open-sourced models and inference code as a foundation for building applications and further research on robust speech processing. |
| License | The Vosk API GitHub repository identifies its license as Apache-2.0. | Whisper's code and model weights are released under the MIT License. |
| Model sizes | Small models are typically around 50 MB and require about 300 MB of runtime memory; large server models can require up to 16 GB. | The repository provides tiny, base, small, medium, large and turbo model sizes, with English-only variants for the first four. |
Vosk plans
- Vosk Open SourceFree
Whisper plans
- Self-hosted WhisperFree
- Whisper (open-source code and model weights)Free
- Whisper API$0.01 a month
Pick Vosk if…
Vosk suits developers building applications that need offline or streaming speech recognition. Its different model sizes and language bindings offer options for lightweight devices and server deployments.
Pick Whisper if…
Whisper may suit developers and researchers building speech-processing applications or exploring multilingual transcription and translation. It is also an option for people comfortable installing and running command-line or Python software locally.