| title | iga-multi-tts |
|---|---|
| app_file | app.py |
| sdk | gradio |
| sdk_version | 6.6.0 |
A simple web-based tool for recording audio from your microphone, trimming it to the desired length, and downloading as a .wav file.
- Record Audio: Click to record audio directly from your microphone
- Trim Audio: Use dual sliders to select the exact start and end times
- Real-time Feedback: See total duration and selected duration as you adjust
- Download: Export trimmed audio as a .wav file
- Clean Interface: Simple, intuitive Gradio UI
- Click the microphone icon to start recording
- Speak or play audio into your microphone
- Click stop when finished
- Adjust the start and end sliders to select the portion you want to keep
- Click "Trim & Download" to generate the trimmed audio
- Right-click on the audio player to download the .wav file
conda env create --env=environment.yaml
conda activate iga-tts
pip install -r requirements.txt
python app.pyThe app will launch at http://localhost:7860
Can be deployed on Hugging Face Spaces or any platform supporting Gradio apps.
gradio deployCurrent gradio app deployed and available at: Space
- gradio: Web UI framework
- soundfile: Audio file I/O
- numpy: Audio data processing