Voice AI / Space
    Submit
    Back
    Voicebox

    Voicebox

    Visit Website
    Tech
    Voice Cloning
    Open Source

    Open-source desktop application for local voice cloning and speech generation.

    Voicebox banner

    About Voicebox

    Voicebox: The Open-Source AI Voice Studio

    Voicebox is an open-source desktop application designed for voice cloning, dictation, and speech generation. Operating entirely on your local machine, it serves as a free alternative to cloud-based platforms like ElevenLabs and WisprFlow. The application is available for macOS, Windows, and Linux, allowing users to clone voices, generate speech across multiple text-to-speech engines, and interact with AI agents using custom voices.

    Key Features

    • Voice Cloning: Clone any voice using as little as three seconds of audio by uploading files (WAV, MP3, FLAC, WebM), recording from a microphone, or capturing system audio.
    • Stories Editor: A timeline-based editor to create multi-voice narratives, arrange tracks, trim clips, and mix conversations between characters.
    • Audio Effects Pipeline: Apply and preview effects like pitch shift, reverb, delay, and compression, and save them as default presets per voice profile.
    • Local and Remote Inference: Run GPU inference locally using Metal, CUDA, ROCm, Intel Arc, or DirectML, or connect to a remote machine with one-click server setup.
    • Audio Transcription: Powered by Whisper models (Base, Small, Medium, Large, and Turbo) supporting 99 languages, with an optional local LLM to clean up filler words and punctuation.
    • Unlimited Generation Length: Generate up to 50,000 characters at once, with text automatically split at sentence boundaries and crossfaded seamlessly.
    • System-Wide Dictation: Use a keyboard shortcut to dictate text directly into any application's text field or your clipboard.
    • MCP Agent Integration: Connect with MCP-aware agents like Claude Code, Cursor, and Cline to have them speak back to you in cloned voices.
    • Voice Personalities: Assign free-form personalities to voice profiles to rewrite text or compose original lines in character.
    • Built-in REST API: Access a local API endpoint for programmatic control without API keys, rate limits, or per-character fees.

    Use Cases

    • Games: Generate NPC dialogue on the fly, localize characters into new languages, and create expressive voice lines without a studio.
    • Apps and Agents: Provide applications or AI agents with real-time narration, accessibility readouts, and voice replies.
    • Scripts and Tools: Batch-generate audiobook chapters, automate podcast intros, or integrate Voicebox into a Stream Deck.

    Pricing

    Voicebox is a free, open-source application. It operates locally with no subscriptions, no API keys, no rate limits, and no per-character fees.

    Getting Started

    Website: https://voicebox.sh/

    Voicebox provides a comprehensive, offline solution for creators and developers needing high-quality voice cloning, transcription, and speech generation directly on their own hardware.