Use CasesFully Local Voice Coding with OpenCode

🔒

Fully Local Voice Coding with OpenCode

The Problem

Cloud AI services require internet, send code to third parties, and have latency. Some projects require air-gapped development.

The Solution

Combine OpenCode interrupt with Ollama for a 100% local voice coding pipeline. Everything runs on your machine — LLM inference, transcription, and TTS.

Workflow

  1. Install Ollama and pull a model (ollama pull codellama or similar). Configure OpenCode to use the local Ollama endpoint.
  2. Add the interrupt plugin. Install whisper.cpp with the small or medium model for local transcription.
  3. Install sox for mic access. Edge-tts caches voice data after first use for offline TTS.
  4. Start OpenCode. Type /ptt to speak, hear responses via TTS, interrupt with voice. All processing is local.
  5. No data ever leaves your machine. No API keys needed. Works fully offline after initial setup.
Tips
• Use the medium whisper model for best local transcription accuracy. It's 1.5GB but provides results close to OpenAI API.
• Ollama models vary in quality. Mistral and CodeLlama are good for coding. Llama 3 provides the best overall responses.
• Edge-tts needs internet only for the first request per voice. After that, voice data is cached locally.

Want to try this workflow?

Install interrupt →