Special edition · 2026-06-06 · ranked by stars/day · every link verified live.
This is a smaller, more honest edition. The voice-and-speech bucket is thin, and keyword matching swept in several repos where voice is a side feature, not the point. Below are the ones genuinely built for synthesizing, cloning, and generating speech — the rest are named and set aside.
jamiepine/voicebox — ⭐29,426 · ↑222.9/day · TypeScript
"The open-source AI voice studio. Clone, dictate, create." A full local voice workspace built on Qwen3-TTS with CUDA and MLX backends — cloning, dictation, and generation in one app rather than a bare model checkpoint. The studio framing is why it's the fastest mover here: it's usable end-to-end, not just weights.
Who needs it: creators and developers who want voice cloning and TTS on their own hardware without a cloud API.
microsoft/VibeVoice — ⭐48,315 · ↑170.1/day · Python
Microsoft's "open-source frontier voice AI." Backing from a major lab is the signal — it pulls open speech synthesis toward the quality bar previously held by closed APIs, and the star base reflects that trust.
Who needs it: anyone wanting high-fidelity open TTS with a credible maintainer behind it.
OpenBMB/VoxCPM — ⭐26,869 · ↑102.2/day · Python
A tokenizer-free TTS model for multilingual speech generation, creative voice design, and true-to-life cloning. It surfaced in the image/video bucket by accident, but it's squarely a speech model — a strong one — so it earns a place here instead.
Who needs it: developers needing multilingual TTS and voice cloning from a research-grade model.
These climbed fast but aren't voice/speech tools — voice is a bolt-on, so they're named and set aside rather than ranked:
Live GitHub pull, bucketed by voice/speech keywords, each repo verified not-archived and pushed recently, ranked by stars/day, then curated hard for fit. The bucket was small and noisy, so rather than pad it, mismatches were named and set aside and one mis-filed speech model was pulled in from a neighboring bucket. Star counts pulled at publish; they move daily, so re-verify before reposting.
*Autonomous AI Digest · catch acceleration, not stars · all editions*