Audio
dia
A TTS model capable of generating ultra-realistic dialogue in one pass.
★ 19.4k starsApache-2.0
View guide →// audio · fluxions-ai/vui
vui
vui is an open-source audio project by fluxions-ai (fluxions-ai/vui on GitHub). It has 767 GitHub stars and 84 forks, is released under the Custom license, and was last updated on GitHub on 3 October 2026.
A tiny conversational TTS model with cloning, streaming, and CPU speed.
💎 Hidden gem★ 767 stars⑂ 84 forksCustomupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- fluxions-ai/vui
- GitHub stars
- 767
- Forks
- 84
- License
- Custom
- Last updated on GitHub
- 3 October 2026
- Category
- Audio
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Grab the model
Download the lightweight Nano weights.
- Run on CPU
Launch the dependency-free C build — no GPU needed.
- Speak conversationally
Generate context-aware speech with cloning and streaming.
- Use the assistant
Or run the bundled real-time voice assistant stack.
// features
Why people love it
219M active params
Small conversational model trained on real dialogue.
CPU inference
Dependency-free C build runs on ordinary processors.
Voice cloning
Clone voices with streaming synthesis.
Real-time assistant
Ships WebRTC, ASR, and a local LLM stack.
OpenAI Realtime compatible
Drop-in local target for Realtime API clients.
On-device design
Edge-friendly with no cloud dependency.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/fluxions-ai/vui.git cd vui - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Build a voice assistant that runs on a laptop.
- Add conversational TTS to edge devices.
- Prototype realtime voice apps without GPU costs.
- Experiment with small conversational speech models.
Advertisement
// faq
Questions, answered
Who maintains vui?
It is an open-source project at fluxions-ai/vui with 84 forks. Check the repo's contributors and recent commits to see how active maintenance is.
Is vui free for commercial use?
It uses a custom license — read the repo's terms before using it commercially.
Can it really run on CPU?
Yes — the dependency-free C build is designed for CPU inference.
What is the bundled assistant?
A full real-time voice assistant with WebRTC, ASR, and a local LLM, OpenAI Realtime API compatible.
How big is the model?
Vui Nano has 219M active parameters out of 305M total.
// keep exploring
Similar tools
Audio
F5 TTS
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
★ 15.3k starsMIT
View guide →Audio
EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
★ 8.5k starsApache-2.0
View guide →Audio
MOSS-TTS-Nano
MOSS-TTS-Nano: a 0.1B open multilingual speech model that clones voices and streams in real time on CPU
★ 4.5k starsApache-2.0
View guide →Audio
GPA
GPA — one tiny model that does ASR, TTS and voice conversion (General Purpose Audio).
★ 3.1k starsApache-2.0
View guide →Audio
VieNeu-TTS
Vietnamese TTS with instant voice cloning — on-device, real-time CPU inference, 48 kHz audio
★ 2.8k starsApache-2.0
View guide →// alternatives
Alternatives in Audio
The most-starred other Audio projects in the LibreAI catalogue — the realistic shortlist if vui is not the right fit.
- MoneyPrinterTurbo★ 128.3k
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
- Whisper★ 109.9k
Robust Speech Recognition via Large-Scale Weak Supervision
- GPT-SoVITS★ 62.3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Real-Time-Voice-Cloning★ 60.2k
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
- whisper.cpp★ 54.1k
Port of OpenAI's Whisper model in C/C++
// more in audio
More in Audio
Nearby Audio projects in the catalogue, closest in stars to vui — keep exploring the shelf either side of it.
- NotelyVoice★ 803
100% private voice transcription for Android and iOS, on-device.
- cboard★ 759
Free AAC communication boards with text-to-speech, in the browser.
- TTS-Voice-Wizard★ 809
Speech-to-text-to-speech for VRChat, VTubers, and streamers.
- TranscriptionSuite★ 759
Fully local transcription with diarization, for every desktop OS.
- voxt★ 853
A macOS voice assistant that turns speech into actions and notes.
- dictionariez★ 674
Double-click any word for definitions, speech, translation, and Anki.
Get vui
Free and open — grab the source, star the repo, and start creating.