packages/kilo-docs/pages/code-with-ai/features/speech-to-text.md
Use voice input in prompt fields instead of typing. When the Kilo provider is enabled and you are signed in, the microphone appears automatically and transcription uses your account through Kilo Gateway.
Voice input needs FFmpeg plus access to the Kilo provider.
FFmpeg is required for audio capture and processing. Install it for your platform:
macOS:
brew install ffmpeg
Linux (Ubuntu/Debian):
sudo apt update
sudo apt install ffmpeg
Windows: Download from ffmpeg.org/download.html and add to your system PATH.
Enable and sign in to the Kilo provider to use voice input in prompt fields. Requests use your Kilo account through Kilo Gateway, so no separate OpenAI provider profile or API key is needed.
You can optionally choose a transcription model in Settings > Experimental > Speech to Text Model. Kilo stores this choice as experimental.speech_to_text_model in your global Kilo CLI config (~/.config/kilo/kilo.jsonc).
When you are signed in to the enabled Kilo provider, a microphone button appears in prompt fields:
The feature includes real-time audio level visualization and voice activity detection to automatically detect when you're speaking.
Microphone button not appearing:
Transcription errors:
Voice transcription has these requirements: