Voice dictation is here
Talk to your codebase. Anime now supports voice input for hands-free coding sessions.
Starting with Anime v0.2.100, you can dictate your prompts instead of typing them. This feature is built on top of the system's native speech recognition APIs and works entirely locally — no audio data leaves your machine.
How it works
Press Ctrl+V in the prompt to toggle voice mode. Anime will start listening through your default microphone and transcribe your speech in real time. When you pause speaking, the transcription is submitted as your prompt.
This is especially useful during long refactoring sessions where you want to describe high-level changes without breaking your flow — things like:
Supported platforms
Voice dictation is currently available on:
- ✓ macOS — uses the built-in Speech Recognition framework
- ✓ Linux — uses PipeWire/PulseAudio with Whisper.cpp for local transcription
Windows support is coming in a future release.
Configuration
You can customize the voice input behavior in your config file: