Alternatives and similar repositories for StyleTTS2-lite:

Users that are interested in StyleTTS2-lite are comparing it to the libraries listed below

• duerig / StyleTTS2
  StyleTTS 2 Optimized Training Fork
  ☆27Updated 3 months ago
• Stylish-TTS / stylish-tts
  High quality text-to-speech based on StyleTTS 2.
  ☆37Updated this week
• iamanigeeit / present
  ☆13Updated 8 months ago
• jakariaemon / WSI
  Whisper Speaker Identification (WSI), a cutting-edge model for multilingual speaker identification.
  ☆16Updated last month
• uthree / ddsp-vocoder
  ☆10Updated 5 months ago
• ShoukanLabs / Vokan
  The Vokan Architecture (Tsukasa speech based)
  ☆9Updated 2 months ago
• MaxMax2016 / Glow-SVC
  4G GPU & 10 Minutes for train
  ☆12Updated last year
• reppy4620 / convnext_tts
  Unofficial implementation of ConvNeXt-TTS powered by lightning
  ☆17Updated 6 months ago
• Respaired / RiFornet_Vocoder
  a Neural Vocoder supporting Ring Attention, Conformer and NSF.
  ☆18Updated 2 months ago
• ex3ndr / supervoice-vocoder
  Production-ready vocoder using BigVSAN
  ☆11Updated last year
• yxlu-0102 / IDEA-TTS
  Incremental Disentanglement for Environment-Aware Zero-Shot Text-to-Speech Synthesis
  ☆24Updated last month
• OlaWod / PitchVC
  PitchVC: Pitch Conditioned Any-to-Many Voice Conversion
  ☆34Updated 11 months ago
• shinhyeokoh / rwen
  ☆14Updated last year
• shivammehta25 / BetterFastSpeech2
  Just another FastSpeech 2 but cleaner code :)
  ☆26Updated 10 months ago
• ZehuaKcrissLi / GTR-Voice
  ☆13Updated 5 months ago
• Plachtaa / ASTRAL-quantization
  speaker-disentangled speech linguistic content quantizer
  ☆14Updated last month
• caizexin / GenVC
  Self-supervised Generative LM-based Voice Conversion
  ☆27Updated last week
• ex3ndr / supervoice-hybrid
  My hybrid TTS network that combines, VALL-E, VoiceBox, SpeechFlow, Seamless and TortoiseTTS into one
  ☆27Updated 9 months ago
• Tikai7 / DiTTO-TTS
  DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors
  ☆19Updated 2 months ago
• MiscellaneousStuff / PhoneLM
  (R&D) Text to speech using phonemes as inputs and audio codec codes as outputs. Loosely based on MegaByte, VALL-E and Encodec.
  ☆48Updated last year
• declare-lab / HyperTTS
  ☆35Updated last year
• SLPcourse / Singing-Voice-Conversion
  Project of Singing Voice Conversion.
  ☆14Updated last year
• fakerybakery / OpenF5-TTS
  (WIP) A retrain of F5-TTS on permissively-licensed data
  ☆11Updated 3 weeks ago
• pengzhendong / audio-pipeline
  ☆20Updated 6 months ago
• reppy4620 / vocoders
  My vocoder experiments
  ☆28Updated 6 months ago
• gwx314 / TechSinger
  TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching
  ☆49Updated 2 weeks ago
• p0p4k / vits3_pytorch
  ☆29Updated last year
• huutuongtu / Lightvoc
  LIGHTVOC AN UPSAMPLING-FREE GAN VOCODER BASED ON CONFORMER AND INVERSE SHORT-TIME FOURIER TRANSFORM
  ☆16Updated 11 months ago
• yoongi43 / VRVQ
  Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"
  ☆13Updated 3 weeks ago
• choiHkk / Transformer-TTS-V2
  ☆26Updated last year