AI GitHub
Pedalboard for processing generated audio in Python
Apply audio effects and load supported plugins when editing model-generated audio.
Key Takeaways
- Pedalboard gives Python code a way to assemble effect chains and read or write audio.
- Start with a supported audio format and a known sample rate.
- Apply compression and a gain adjustment to one speech clip, then compare loudness and clipping with the original.
- Plugin availability and behavior vary by platform.
How it works
Pedalboard gives Python code a way to assemble effect chains and read or write audio. It fits after synthesis when a production workflow needs repeatable processing.
What you need
Start with a supported audio format and a known sample rate. An external effect plugin adds platform and installation requirements that a built-in effect may avoid.
What to try first
Apply compression and a gain adjustment to one speech clip, then compare loudness and clipping with the original. Render the same chain twice with fixed settings.
Process a clip with a quiet opening and a loud ending. Compare waveform peaks and listen for pumping after compression instead of trusting output level alone.
Where to look for failures
Plugin availability and behavior vary by platform. Keep an unprocessed source and log effect settings so a render can be reproduced.
Related Franklin pages
Keep generation and editing as separate reproducible steps. A waveform or processed clip should have a reference to the raw model output and its settings.
- Generate speech and experiment with reference audio and documented expression controls. Chatterbox for controllable text-to-speech
- Experiment with published generative audio models and training components. AudioCraft for music and sound generation research
For an application where the quality of recording and handling audio matters, see Franklin’s Open Mic AI profile. Open Mic AI
Project documentation
Try it for your workflow
Explore the project’s documentation for setup and usage, or save this page to a collection for later.
Read the project documentation ↗