jamiepine/voicebox

Health v2 · maintenance only

Adoption not part of the score

57872 stars · 7252 forks observed · 2026-10-18

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-21, confidence 0.97

Voicebox is an open‑source, local‑first AI voice studio that lets you clone voices, generate speech in many languages, and dictate into any app. It runs entirely on your machine and offers optional encrypted cloud backup via a token.

Use cases

• Clone a new voice from a few seconds of audio and use it for text‑to‑speech.
• Generate natural‑sounding speech in multiple languages for videos or podcasts.
• Dictate into any application using a global hotkey and capture audio with transcript.
• Give a custom voice to an AI agent or chatbot for more immersive interactions.
• Create and manage voice profiles with personas for storytelling or content creation.

When to choose

• You need offline, privacy‑preserving voice cloning and TTS without sending data to the cloud.
• You want a free, open‑source desktop solution that works on Windows, macOS, and Linux.
• You require customizable voice personas and integration with local LLMs for voice refinement.

When to avoid

• You need high‑throughput, enterprise‑grade cloud TTS with SLA guarantees.
• Your hardware cannot run GPU‑accelerated models required for high‑quality voice synthesis.
• You prefer a web‑only service with no installation or maintenance overhead.

Facets

application · maturity active

audio-processing nlp llm-inference cli artificial-intelligence speech-processing computer-vision windows voice-cloning tts dictation local-first open-source cloud-backup-optional token-supported speech-processing macos linux desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="jamiepine/voicebox")