GStars
    k2-fsa

    k2-fsa/OmniVoice

    High-Quality Voice Cloning TTS for 600+ Languages

    backend
    Python
    Apache-2.0
    16.2K stars
    2.4K forks
    16.2K GitHub watchers
    Updated Nov 3, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    No releases in the last 90 days; the most recent was 109 days ago, with 21 contributors on GitHub.

    Peaked at #22 in the weekly ranking the week of Sep 13, its best in the past year.

    Use Cases & Benefits

    • Provides a massively multilingual zero-shot text-to-speech model supporting over 600 languages with voice cloning and voice design capabilities.
    • Delivers high-quality speech synthesis with fast inference speed using a novel diffusion language model-style architecture.
    • Use for cloning a specific speaker's voice from a short audio sample to generate personalized speech in multiple languages.
    • Use for designing custom voices by specifying speaker attributes like gender, age, pitch, and accent without reference audio.
    • Use for batch processing large-scale TTS tasks with multi-GPU support and accelerated inference via FlashInfer integration.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    Apache 2.0

    Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.

    Community files

    • README: present
    • Contributing guide: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    OmniVoice is a state-of-the-art massively multilingual zero-shot text-to-speech (TTS) model supporting over 600 languages. Built on a novel diffusion language model-style architecture, it generates high-quality speech with superior inference speed, supporting voice cloning and voice design.

    Choose one of the following methods: pip or uv.

    Excerpt from the k2-fsa/OmniVoice README on GitHub (Apache-2.0 license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Sep 6: +178Sep 7: +329Sep 8: +292Sep 9: +124Sep 12: +513Sep 13: +218Sep 14: +270Sep 15: +45Sep 19: +44Sep 20: +46Sep 21: +56Sep 22: +43Sep 23: +52Sep 24: +50Sep 25: +34Sep 26: +34Sep 27: +39Sep 28: +74

    +6,354 stars over 59 days across 25 snapshot days; best day +513 on Sep 12.

    Forks

    2.4K+764

    Open issues

    78+20

    Compared with peers in Backend

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    View category →
    k2-fsa/OmniVoice compared with Backend repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    anthropics/skills192.3K+5.2K75—
    zed-industries/zed94.7K+2.3K756 days ago
    google/skills23.8K+2.0K75—
    NationalSecurityAgency/ghidra99.4K+1.8K7519 days ago
    DuarteSantos8/openGym20.8K+1.7K757 days ago
    k2-fsa/OmniVoice16.2K—37109 days ago
    Category median94.7K+2.0K75—
    Compare OmniVoice with skills, zed, skills →

    Also by k2-fsa

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description