speaches
A self-hosted speech-to-text and transcription platform
About
Speaches is a self-hosted transcription and speech-to-text platform. It processes audio files or streams and provides text output, timestamps, and export options via a web interface.
Languages
Contributors30
![renovate[bot]](https://avatars.githubusercontent.com/in/2740?v=4)
- Speech-to-TextCore
Convert speech audio into text
- API ServiceCore
Provide speech recognition via API
- Language SupportCore
Recognize speech in supported languages
- Batch Processing
Process multiple audio files
- Output Formats
Export transcriptions in common formats
- Self-Hosted Deployment
Run speech recognition on your own infrastructure
Comments Theme
Install
docker_compose
