anan235 / dia-multilingualLinks
A TTS model capable of generating ultra-realistic dialogue in one pass.
☆213Updated 5 months ago
Alternatives and similar repositories for dia-multilingual
Users that are interested in dia-multilingual are comparing it to the libraries listed below
Sorting:
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆125Updated 2 months ago
- ☆282Updated 2 months ago
- SoTA open-source TTS☆96Updated 4 months ago
- Automatically cleaning, enhancing, segmenting, filtering, and formatting a dataset to fine tune or train a voice model.☆42Updated 3 weeks ago
- Streaming and Fine-tuning for Chatterbox TTS☆193Updated 3 months ago
- ☆275Updated last year
- VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration☆185Updated 5 months ago
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆126Updated 2 months ago
- ☆99Updated last year
- Real-time Speech-Text Foundation Model Toolkit (wip)☆247Updated 6 months ago
- ☆261Updated last year
- StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion☆186Updated last year
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆284Updated 4 months ago
- 🐍 🤖 Pip installable package for StyleTTS 2 human-level text-to-speech and voice cloning☆157Updated last year
- LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆618Updated 6 months ago
- Fine Tune the Style-TTS2 Voice Model☆253Updated 3 months ago
- 🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.☆251Updated last year
- G2P☆323Updated 2 months ago
- Very fast, accurate speaker diarization☆145Updated last week
- ☆307Updated last week
- Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis☆307Updated 2 months ago
- ☆46Updated this week
- ☆378Updated last year
- A random walk voice style cloning application for Kokoro text to speech☆142Updated 3 months ago
- VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency☆146Updated this week
- Collection of Open Source Speech Data☆160Updated last week
- ☆183Updated last month
- ☆258Updated last month
- Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch☆502Updated 6 months ago
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆66Updated 10 months ago