Voicebox: Local Open Source Voice Studio
aigclink · x · 2026-07-19
Voicebox is an open source, local-first voice app focused on two main functions: text-to-speech and speech-to-text. It supports instant voice cloning from a few seconds of audio and global hotkey dictation into any input box. Emphasizing privacy, all models, voice data, and recordings can be kept entirely on the local machine.
The author notes that it supports a variety of TTS engines, including Qwen3-TTS, Qwen CustomVoice, LuxTTS, Chatterbox, HumeAI TADA, and Kokoro. It also handles multi-voice cloning, synthesizes podcast-style dialogues, and offers post-processing effects, a multi-track editor, and chunked processing for long audio. Crucially, it provides a voicebox.speak tool call that integrates with code agents like Claude Code, Cursor, and Cline, allowing agents to execute voice tasks using a cloned voice.
Related event: Voicebox Debuts as Open-Source Local Voice Studio(3 posts)→
More from coding & agent
- MathModelAgent gains traction: auto-solves math modeling and writes a submission-ready paper — jihe520 · 2026-09-11
- alphaXiv open-sources OpenResearch to run parallel research agents with any model — alphaXiv · 2026-09-11
- DeskcommCRM: open-source AI sales CRM with native agents and WhatsApp hits 1k stars — melgarafael · 2026-09-11
- hyperresearch: agent-driven knowledge base that turns web research into a searchable wiki — jordan-gibbs · 2026-09-11
- Forter's 13 lessons from its agent sprint: skip custom RAG, lean on mature enterprise search — bibryam · 2026-09-11
- Two real 'company brains' opened up live: Gorgias' in-house Cortex vs Slite — femke_plantinga · 2026-09-11