ysharma3501/LuxTTS
luxtts
A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.
Builder
ysharma3501
ysharma3501 • individual
Stars
3,540
Using upstream star count
Forks
439
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Jan 23, 2026
Project creation date
README Summary
LuxTTS is a high-quality text-to-speech voice cloning model designed for rapid synthesis, achieving impressive speeds of 150x realtime performance. The model focuses on delivering both quality and speed for voice synthesis applications. It appears to be built with Python and optimized for fast inference.
AI Dev Skills
Unmapped
Text-to-Speech SynthesisVoice CloningNeural Audio GenerationReal-time Audio ProcessingDeep Learning Inference OptimizationMel-Spectrogram GenerationVocoder Implementation
Tags
Text-to-Speech SynthesisVoice CloningNeural Audio GenerationReal-time Audio ProcessingDeep Learning Inference OptimizationMel-Spectrogram GenerationVocoder ImplementationAccessibility TechnologyOn-premiseContent CreationVoice Assistant DevelopmentAudioEfficient Neural NetworksAudiobook NarrationSelf-hostedMedia & EntertainmentEdge/MobileContent DubbingReal-time Speech SynthesisTextOn-device AIGamingPersonalized Voice GenerationEducationReal-time AI ProcessingPython
Taxonomy
Deployment Context
Skill Areas
Recent Activity
Updated 1 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
prototype- Quality
- medium
- Maturity
- prototype
Categories
Inference & ServingPrimaryEdge & Mobile AIOther AI / MLGenerative Media
PM Skills
Scale & ReliabilityCost & Efficiency
Languages
Python100.0%
Timeline
- Project created
- Jan 23, 2026
- Forked
- Mar 23, 2026
- Your last push
- 1 months ago
- Upstream last push
- 1 months ago
- Tracked since
- Mar 12, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…