Knuckles-Team/audio-transcriber
3.3
If you are the rightful owner of audio-transcriber 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.
Audio-Transcriber is a versatile tool designed to transcribe audio files into text using advanced models, including OpenAI's Whisper. It supports various audio formats and offers features for recording and exporting transcriptions.
Audio-Transcriber
Version: 0.5.52
Transcribe your .wav .mp4 .mp3 .flac files to text or record your own audio!
This repository is actively maintained - Contributions are welcome!
Contribution Opportunities:
- Support new models
Wrapped around OpenAI Whisper
Usage:
| Short Flag | Long Flag | Description |
|---|---|---|
| -h | --help | See Usage |
| -b | --bitrate | Bitrate to use during recording |
| -c | --channels | Number of channels to use during recording |
| -d | --directory | Directory to save recording |
| -e | --export | Export txt, srt, and vtt files |
| -f | --file | File to transcribe |
| -l | --language | Language to transcribe |
| -m | --model | Model to use: <tiny, base, small, medium, large> |
| -n | --name | Name of recording |
| -r | --record | Specify number of seconds to record to record from microphone |
Example:
audio-transcriber --file '~/Downloads/Federal_Reserve.mp4' --model 'large'
audio-transcriber --record 60 --directory '~/Downloads/' --name 'my_recording.wav' --model 'tiny'
Model Information:
Courtesy of and Credits to OpenAI: Whisper.ai
| Size | Parameters | English-only model | Multilingual model | Required VRAM | Relative speed |
|---|---|---|---|---|---|
| tiny | 39 M | tiny.en | tiny | ~1 GB | ~32x |
| base | 74 M | base.en | base | ~1 GB | ~16x |
| small | 244 M | small.en | small | ~2 GB | ~6x |
| medium | 769 M | medium.en | medium | ~5 GB | ~2x |
| large | 1550 M | N/A | large | ~10 GB | 1x |
Installation Instructions:
Use with AI
Configure mcp.json
{
"mcpServers": {
"audio_transcriber": {
"command": "uv",
"args": [
"run",
"--with",
"audio-transcriber",
"audio-transcriber-mcp"
],
"env": {
"WHISPER_MODEL": "medium", // Optional
"TRANSCRIBE_DIRECTORY": "~/Downloads" // Optional
},
"timeout": 200000
}
}
}
Deploy MCP Server as a container
docker pull knucklessg1/audio-transcriber:latest
Modify the compose.yml
services:
audio-transcriber:
image: knucklessg1/audio-transcriber:latest
environment:
- HOST=0.0.0.0
- PORT=8021
ports:
- 8021:8021
Install Python Package
python -m pip install audio-transcriber
or
uv pip install --upgrade audio-transcriber
Ubuntu Dependencies
sudo apt-get update
sudo apt-get install libasound-dev portaudio19-dev libportaudio2 libportaudiocpp0 ffmpeg gcc -y
Repository Owners:
