Reposby Glyph
tacotron2 license, foundation and stars
Image, video and speech generation · BSD 3-Clause (open source) · backed by Nvidia · 5,305 stars
Tacotron 2 - PyTorch implementation with faster-than-realtime inference
License history
LICENSE fileBSD 3-Clause No license change recorded since the repository was created in 2018.
Latest release
No GitHub releases published; the project releases elsewhere (tags or its own site).
More in image, video and speech generation
stable-diffusion-webuiStable Diffusion web UI.+24 a week
ComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.+1,572 a week
stable-diffusionA latent text-to-image diffusion model.+16 a week
GPT-SoVITS1 min voice data can also be used to train a good TTS model!+368 a week
Real-Time-Voice-CloningClone a voice in 5 seconds to generate arbitrary speech in real-time.+12 a week
VibeVoiceOpen-Source Frontier Voice AI.Microsoft · +338 a week
FooocusFocus on prompting and generating.+100 a week
VoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning.+581 a week| Project | Stars | |||
|---|---|---|---|---|
 stable-diffusion-webuiStable Diffusion web UI.AGPL v3 | AGPL v3 | 165k | +24 | - |
 ComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.GPL v3 | GPL v3 | 146k | +1,572 | - |
 stable-diffusionA latent text-to-image diffusion model.Custom or mixed (see the LICENSE file) | Custom or mixed (see the LICENSE file) | 73.6k | +16 | - |
 GPT-SoVITS1 min voice data can also be used to train a good TTS model!MIT | MIT | 64.7k | +368 | - |
 Real-Time-Voice-CloningClone a voice in 5 seconds to generate arbitrary speech in real-time.Custom or mixed (see the LICENSE file) | Custom or mixed (see the LICENSE file) | 60.2k | +12 | - |
 VibeVoiceOpen-Source Frontier Voice AI.MicrosoftMIT | MIT | 56.9k | +338 | - |
 FooocusFocus on prompting and generating.GPL v3 | GPL v3 | 53.9k | +100 | - |
 VoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning.Apache 2.0 | Apache 2.0 | 42k | +581 | - |
About and history
- Repository
- NVIDIA/tacotron2 · created May 3, 2018
- Language
- Jupyter Notebook
- Foundation
- None; run by Nvidia
- Company
- Nvidia · on Companies · on Acquisitions · on awards · on blogs · on certifications · on Quarterly · on Mainstage · on Leaders · on Arena · on marketplaces · on papers · on Allied · on Paydays · on predictions · on quotes · on Releases · on TechConf · on training · on Hotlist
- GitHub detects
- BSD-3-Clause
- Stars per week
- 2 (GitHub weekly snapshots)
Weekly snapshots
| Week of | Stars | |
|---|---|---|
| Nov 2, 2026 | 5,305 | |
| Oct 26, 2026 | 5,303 | |
| Oct 12, 2026 | 5,299 | |
| Oct 5, 2026 | 5,296 | |
| Sep 21, 2026 | 5,295 |