Fast-Whisper-MCP-Server
If you are the rightful owner of Fast-Whisper-MCP-Server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A high-performance speech recognition MCP server based on Faster Whisper, providing efficient audio transcription capabilities.
The Whisper Speech Recognition MCP Server is a robust and efficient solution for audio transcription, leveraging the capabilities of Faster Whisper. It is designed to handle batch processing and offers automatic CUDA acceleration for enhanced performance. The server supports multiple model sizes, from tiny to large-v3, and provides output in various formats such as VTT subtitles, SRT, and JSON. It is optimized for batch transcription of audio files and includes features like model instance caching and dynamic batch size adjustment based on GPU memory. This makes it a versatile tool for developers and businesses looking to integrate speech recognition into their applications.
Features
- Integrated with Faster Whisper for efficient speech recognition
- Batch processing acceleration for improved transcription speed
- Automatic CUDA acceleration (if available)
- Support for multiple model sizes (tiny to large-v3)
- Output formats include VTT subtitles, SRT, and JSON
Tools
get_model_info
Get information about available Whisper models
transcript
Transcribing a single audio file
batch_transcribe
Batch transcription of audio files in folders
