voice-vibecoder 2.26.2

Olaf The Vibecoder — a voice-controlled coding assistant using OpenAI Realtime API + Claude Code

Olaf The Vibecoder

Talk to your codebase like a colleague. You speak an idea; Olaf holds a natural voice conversation while coding agents (Claude Code and friends) quietly build it on separate git branches. Ask to see the diff, say "merge it", and it lands on main — the whole loop, hands-free.

you:   "lag en fil med et dikt i repoet"
olaf:  "Klart, jeg setter i gang!"          → agent builds on branch 'dikt'
you:   "vis diff"                            → colorized diff in the TUI
you:   "merge det inn i main"
olaf:  "Ferdig! Dikt er merget inn i main."

Quick Start

# Install and run
uv tool install voice-vibecoder
vibecoder

On first launch, a setup wizard will guide you through connecting your OpenAI or Azure OpenAI account. Press s anytime to change settings.

Features

• Natural conversation — full-duplex voice: interrupt Olaf mid-sentence and it stops and listens (system echo cancellation on macOS, adaptive echo gate elsewhere). Short spoken answers, follows your language, resumes previous conversations where they left off
• Invisible agent orchestration — multi-instance Claude Code agents in separate git worktrees; Olaf narrates progress and delivers results
• Voice-driven git — show diffs, merge branches into main, clean up worktrees, all by voice; conflicts are reported, never half-merged
• Live file tree per agent (including files the agent just created) and GitHub-style diff view
• Session persistence across restarts
• Push-to-talk and voice activity detection modes
• OpenAI and Azure OpenAI realtime (GA voices marin/cedar), Gemini Live
• Multi-language (English, Norwegian, Swedish) — spoken and transcribed

Requirements

• Python 3.10+
• An OpenAI API key with Realtime API access
• PortAudio for microphone input (brew install portaudio on macOS)
• Claude Code CLI installed

Usage as a Library

Embed the voice coding screen in your own Textual app:

from pathlib import Path
from voice_vibecoder import VoiceCodingApp, VoiceCodingScreen, VoiceConfig

# Standalone app with custom config
config = VoiceConfig(
    app_name="My Coding Assistant",
    config_dir=Path.home() / ".my-app",
    data_dir=Path.home() / ".my-app",
    log_dir=Path.home() / ".my-app" / "logs",
    on_startup=lambda send: send("Hello from startup!"),
)
VoiceCodingApp(config=config).run()

# Or embed the screen in your own Textual app
screen = VoiceCodingScreen(repo_root, config=config)

Configuration

Settings are stored using platform-standard directories:

Platform	Config	Data	Logs
macOS	~/Library/Application Support/voice-vibecoder/	~/Library/Application Support/voice-vibecoder/	~/Library/Logs/voice-vibecoder/
Linux	~/.config/voice-vibecoder/	~/.local/share/voice-vibecoder/	~/.local/state/voice-vibecoder/log/

Git worktrees are created as siblings of your project directory (e.g., ../my-project-feat-login).

Keyboard Shortcuts

Key	Action
q / Esc	Quit
m	Toggle mute
s	Settings
c	Cancel current Claude task
Space	Push-to-talk (when in PTT mode)

License

MIT