Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Omnigraph
Omnigraph
It's a plan
It's a plan
OfinTech Desk
OfinTech Desk
Bifrost
Bifrost
Busbar
Busbar

OpenBMB/VoxCPM

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

#Text to speech
Visit GitHub
Python
42.6k
5.1k
25 contributors
Apache License 2.0
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Busbar

Control what AI can do before it acts

Momentum

How fast OpenBMB/VoxCPM is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Sep 19 – Nov 18, 2026

Stars +4,844 in 61 days

0200400600
450

Forks +658 in 61 days

0204060
56

Merged PRs 3 in 61 days

012
2

Trendshift Trendingwhere the repository ranked each day it made the top 25

Top 25 in Python

7192322913
Sep 19Sep 27Oct 5Oct 13Oct 21Oct 29Nov 6Nov 14
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRsPython
Sat, Sep 19, 2026+27+20Not trending
Sun, Sep 20, 2026+25+40Not trending
Mon, Sep 21, 2026+29+90Not trending
Tue, Sep 22, 2026+34+70Not trending
Wed, Sep 23, 2026+30+50Not trending
Thu, Sep 24, 2026+35+40Not trending
Fri, Sep 25, 2026+25+30Not trending
Sat, Sep 26, 2026+16+30Not trending
Sun, Sep 27, 2026+22+20Not trending
Mon, Sep 28, 2026+65+70Not trending
Tue, Sep 29, 2026+57+40Not trending
Wed, Sep 30, 2026+102+80Not trending
Thu, Oct 1, 2026+16+30Not trending
Fri, Oct 2, 2026+9+10Not trending
Sat, Oct 3, 2026+19+50Not trending
Sun, Oct 4, 2026+24+50Not trending
Mon, Oct 5, 2026+19+40Not trending
Tue, Oct 6, 2026+26+10Not trending
Wed, Oct 7, 2026+27+30Not trending
Thu, Oct 8, 2026+35+92Not trending
Fri, Oct 9, 2026+40+30Not trending
Sat, Oct 10, 2026+59+50Not trending
Sun, Oct 11, 2026+446+560#7
Mon, Oct 12, 2026+209+330Not trending
Tue, Oct 13, 2026+59+80Not trending
Wed, Oct 14, 2026+77+110Not trending
Thu, Oct 15, 2026+71+100Not trending
Fri, Oct 16, 2026+53+70Not trending
Sat, Oct 17, 2026+54+100Not trending
Sun, Oct 18, 2026+53+60Not trending
Mon, Oct 19, 2026+54+60Not trending
Tue, Oct 20, 2026+39+130Not trending
Wed, Oct 21, 2026+39+50Not trending
Thu, Oct 22, 2026+262+470Not trending
Fri, Oct 23, 2026+303+300#19
Sat, Oct 24, 2026+283+310#23
Sun, Oct 25, 2026+68+120Not trending
Mon, Oct 26, 2026+85+120Not trending
Tue, Oct 27, 2026+68+100Not trending
Wed, Oct 28, 2026+44+50Not trending
Thu, Oct 29, 2026+37+70Not trending
Fri, Oct 30, 2026+36+60Not trending
Sat, Oct 31, 2026+59+50Not trending
Sun, Nov 1, 2026+27+50Not trending
Mon, Nov 2, 2026+36+60Not trending
Tue, Nov 3, 2026+25+40Not trending
Wed, Nov 4, 2026+29+50Not trending
Thu, Nov 5, 2026+71+101Not trending
Fri, Nov 6, 2026+22+40Not trending
Sat, Nov 7, 2026+212+310#22
Sun, Nov 8, 2026+450+470#9
Mon, Nov 9, 2026+322+360#13
Tue, Nov 10, 2026+101+140Not trending
Wed, Nov 11, 2026+113+280Not trending
Thu, Nov 12, 2026+82+60Not trending
Fri, Nov 13, 2026+46+60Not trending
Sat, Nov 14, 2026+29+60Not trending
Sun, Nov 15, 2026+45+100Not trending
Mon, Nov 16, 2026+33+70Not trending
Tue, Nov 17, 2026+31+50Not trending
Wed, Nov 18, 2026+30+10Not trending
Total+4,844+6583
  • 1#1 on the list
  • 7Rank that day
  • Not trending
1
  • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    Jan 18 – Oct 23, 2026#1 on 1 day

    #1#5#10#15#20#25
    Top 10
    Feb 2026AprJunAugOct
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about OpenBMB/VoxCPM, and every badge it has earned
    1. Nov 171 post
      • Tokenizer-free TTS that picks up timbre and emotion from a short sample. VoxCPM reads Chinese polyphones and numbers correctly, keeps long sentences breathing naturally, and runs locally for batch…

        Read full on X, posted by @laogeai

        @laogeai · x.com

    2. Nov 161 post
      • There’s a collection of free projects on GitHub that are already capable of replacing quite a few tools you’re paying for monthly. 1. TradingAgents An AI multi-agent quantitative trading framework 2.…

        Read full on X, posted by @I_am_Aiabir

        @I_am_Aiabir · x.com

    3. Nov 151 post
      • There’s a collection of free projects on GitHub that are already capable of replacing quite a few tools you’re paying for monthly. 1. TradingAgents An AI multi-agent quantitative trading framework 2.…

        Read full on X, posted by @abir35627

        @abir35627 · x.com

    4. Nov 112 posts
      • 3.8万星的语音合成,真分不出真假。 输入「沉稳的30代女声」直接出声,放段录音连口癖都复刻,48kHz。 我试了下,短的像真的,长的还是有点飘。 你们拿它配什么? 仓库:

        Read full on X, posted by @yang3izc

        @yang3izc · x.com

      • Tokenizer-based audio models are officially legacy technology. ⚠️ OpenBMB just dropped VoxCPM2—a 2B parameter, tokenizer-free multilingual TTS engine trained on over 2 million hours of speech data…

        Read full on X, posted by @RituWithAI

        @RituWithAI · x.com

    5. Nov 102 posts
      • FREE AI THAT CLONES ANY VOICE FROM A SHORT CLIP 😳 it's called voxcpm2, an open voice model you can run on your own pc you describe a voice in words or drop a short clip of one and it reads your text…

        Read full on X, posted by @kawaidgaf

        @kawaidgaf · x.com

      • 1. OpenCut-app/OpenCut 开源版 CapCut,免费、MIT 协议,总星快 10 万。 不想再被会员和水印卡住,官方网页版打开就能剪。据项目路线图,后续还有更多功能在做。 🔗 直达: 以前剪片先看会员到期没,现在开网页就剪,169 星一天!🟢🟢

        Read full on X, posted by @CryptoOracle666

        @CryptoOracle666 · x.com

    6. Nov 92 posts
      • Top AI repos on GitHub today | Tue, Nov 10 • milind-soni/OpenMausBot: An open source bot that gets its own virtual machine. It can click, type and run apps there for you. • debpalash/VoiceStudio: A…

        Read full on X, posted by @VT_zero1

        @VT_zero1 · x.com

      • AI 配音开始比拼“声线稳定”了。 开源模型 VoxCPM2 宣称支持30种语言、9种中文方言,能用文字设计音色,也能参考音频调整表达。 但声音能克隆,不等于每条视频都能保持一致;模仿他人声音也要取得授权。 做短视频,你更看重音色一致,还是生成速度?

        Read full on X, posted by @QqqMagic

        @QqqMagic · x.com

    7. Nov 81 post
      • GitHub 热榜第一的 VoxCPM2,曾冲到 3.8 万星。 这是一个开源语音合成模型: 输入约 30 个字,就能生成指定音色 一两秒录音,即可复刻声音 支持 48kHz 音质,项目采用 Apache 2.0 许可证 配音、短视频、播客都能用。 AI 正在把“声音”也变成一种可以直接调用的生产资料。 🔗

        Read full on X, posted by @MapleChenGX

        @MapleChenGX · x.com

    You might also like

    Repositories close to OpenBMB/VoxCPM
    FeaturedAdvertise to 180K+ monthly visitors
    It's a plan

    Open-source Linear alternative

    An issue tracker where AI agents take the work you assign them

    Busbar

    Control what AI can do before it acts

    Omnigraph

    Versioned graph database on object storage. Git-style workflows and multimodal retrieval

    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    OfinTech Desk

    An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

    inclusionAI/Ming-3.0-tts

    Python

    Ming-3.0-tts is an open-source TTS model family with 0.5B dense and 7.9B-A1.3B MoE variants, supporting multilingual speech, voice cloning, voice design, and natural-language control.

    59981

    netease-youdao/Confucius4-TTS

    Python

    Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

    86192

    fishaudio/fish-speech

    Python

    SOTA Open Source TTS

    33.8k3k

    k2-fsa/OmniVoice

    Python

    High-Quality Voice Cloning TTS for 600+ Languages

    16.7k2.5k

    QwenAudio/CosyVoice

    Python

    Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

    24.4k2.9k

    sunnyxrxrx/X-Voice

    Python

    X-Voice

    18521

    Plachtaa/VALL-E-X

    Python

    An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

    7.9k779

    FireRedTeam/FireRedTTS3

    Python

    FireRedTTS3: Multilingual and Multi-Dialect Voice Cloning with Instruction-Guided Voice Design and Speech Editing

    1.7k24

    Zyphra/Zonos

    Python

    Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.

    7.2k739