🎙️ TransMeet — AI-Powered Meeting Summarizer
Turn your meeting recordings into clear, structured minutes using LLMs like Groq Whisper and Google Speech Recognition.
🚀 Features
- ✅ Audio Transcription — Automatically convert
.wavor.mp3files into text - 🧠 LLM-Powered Summarization — Generate concise and structured meeting minutes
- 🔍 Groq & Google Support — Choose between Groq Whisper models or Google Speech API
- 🪓 Automatic Chunking — Splits large files intelligently for smoother transcription
- ⚙️ Fully Customizable — Pick your preferred transcription and summarization models
- 🧾 CLI & Python API — Use it from the terminal or integrate in your Python workflows
- 📁 Clean Output — Saves transcripts and summaries neatly in your desired folder
📦 Installation
pip install transmeet
Dependencies
sudo apt-get update && sudo apt-get install -y ffmpeg gcc && sudo apt-get clean && sudo rm -rf /var/lib/apt/lists/*
🔐 Setup
Set your GROQ API Key/OPENAI API Key in your environment variables.
export GROQ_API_KEY=your_groq_api_key
To make this permanent:
echo 'export GROQ_API_KEY=your_groq_api_key' >> ~/.bashrc
If using OPENAI, set the
OPENAI_API_KEYsimilarly. For Google Speech, no API key is needed; it uses the default model.
🧑💻 How to Use
✅ Option 1: Import as a Python Module
from transmeet import generate_meeting_transcript_and_minutes
generate_meeting_transcript_and_minutes(
meeting_audio_file="/path/to/audio.wav",
output_dir="complete_path_to_output_dir/",
transcription_client="groq", # or "openai"
transcription_model="whisper-large-v3-turbo", # change as per your need
llm_client="groq", # or "openai"
llm_model="llama-3.3-70b-versatile", # change as per your need
)
This will save two files in your output directory:
transcription_<timestamp>.txtmeeting_minutes_<timestamp>.md
🔧 Option 2: Use the CLI
🔹 Basic Usage (Default: GROQ)
transmeet -i /path/to/audio.wav -o output/
🔸 Advanced Usage
transmeet \
-i /path/to/audio.wav \
-o output/ \
--transcription-client groq \
--transcription-model whisper-large-v3-turbo \
--llm-client groq \
--llm-model llama-3.3-70b-versatile \
🗂️ Output Structure
output/
├── transcriptions/
│ └── transcription_20250510_213038.txt
├── meeting_minutes/
│ └── meeting_minutes_20250510_213041.md
🧪 Supported Formats
.wav.mp3
⚙️ CLI Options
| Argument | Description |
|---|---|
-i, --audio-path |
Path to the input audio file |
-o, --output-dir |
Output directory (default: output/) |
--transcription-client |
groq or google (default: groq) |
--transcription-model |
e.g., whisper-large-v3-turbo |
--llm-client |
groq or openai (default: groq) |
--llm-model |
e.g., llama-3.3-70b-versatile |
🤖 LLM Models
- Groq Whisper:
whisper-large,whisper-large-v3-turbo, etc. - Google Speech: Model defaults to their API standard
- LLMs for minutes:
llama-3,mixtral,gpt-4, etc. (Groq/OpenAI)
📋 Roadmap
- Add support for multi-language meetings
- Speaker diarization support
- Upload directly to Notion or Google Docs
- Slack/Discord bots
🧑🎓 Author
Deepak Raj 👨💻 GitHub • 🌐 LinkedIN
🤝 Contributing
Pull requests are welcome! Found a bug or need a feature? Open an issue or submit a PR.
⚖️ License
Metadata
Release files for transmeet 0.0.26
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| transmeet-0.0.26.tar.gz | 17.8 kB | Without provenance | Details for transmeet-0.0.26.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| transmeet-0.0.26-py3-none-any.whl | Python 3 | none | any | Details for transmeet-0.0.26-py3-none-any.whl |
Total release size: 36.1 kB
Release files / transmeet-0.0.26.tar.gz
| Download URL | transmeet-0.0.26.tar.gz |
|---|---|
| Size | 17.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
99ba30bcef335b0c69ca7dcf07ad7c4f76ade23aaf6acc3389f1a7c212c620b8
|
|
BLAKE2b-256 checksum How to use checksums |
1529705ddcbecaf738dc63c6f5da526513781c6ee29e81a88b0b8086225fb6a0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.4
|
Release files / transmeet-0.0.26-py3-none-any.whl
| Download URL | transmeet-0.0.26-py3-none-any.whl |
|---|---|
| Size | 18.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d88ebbbf2db95a6653e779ab6f0594b847a6c9ba36d15b1c8c5885f7aa553bc4
|
|
BLAKE2b-256 checksum How to use checksums |
d4025f172a6539ddca1fc2aa72f4af18ed3fbe3fcf02cca80b1ac4dade4a7db1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.12.4
|
Security for transmeet 0.0.26
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.