Marvis-Labs / marvis-ttsLinks
☆314Updated 3 months ago
Alternatives and similar repositories for marvis-tts
Users that are interested in marvis-tts are comparing it to the libraries listed below
Sorting:
- Liquid Audio - Speech-to-Speech audio models by Liquid AI☆285Updated 2 months ago
- ☆530Updated 2 months ago
- VoiceStar: Robust, Duration-controllable TTS that can Extrapolate☆297Updated 6 months ago
- ☆635Updated last month
- Streaming and Fine-tuning for Chatterbox TTS☆229Updated 5 months ago
- Kyutai with an "eye"☆227Updated 8 months ago
- VLLM Port of the Chatterbox TTS model☆342Updated last month
- List of curated use cases built using Sesame's CSM 1B☆73Updated 6 months ago
- ☆338Updated 2 months ago
- ☆312Updated last month
- Implementation of Sesame's Conversational Speech Model for Hugging Face Transformers☆57Updated 6 months ago
- A highly optimized engine for neutts-air model to generate minutes of audio in seconds. Over 200x realtime on modern hardware!☆57Updated 2 weeks ago
- A TTS model capable of generating ultra-realistic dialogue in one pass.☆216Updated 7 months ago
- Unofficial WIP LoRa Finetuning repository for VibeVoice☆283Updated 2 months ago
- ☆205Updated last month
- A random walk voice style cloning application for Kokoro text to speech☆180Updated 5 months ago
- Sesame Converse - Real Time Conversations - Powered by Gemma 3☆64Updated 8 months ago
- LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM☆291Updated 6 months ago
- Fast Streaming TTS with Orpheus + WebRTC (with FastRTC)☆345Updated 8 months ago
- Very fast, accurate speaker diarization☆186Updated this week
- ☆289Updated 4 months ago
- VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration☆193Updated 7 months ago
- 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets ✨☆128Updated 4 months ago
- Lightweight Gradio based WebUI for orpheusTTS - WSL / Linux [CUDA]☆105Updated 3 weeks ago
- Sesame CSM 1B Voice Cloning☆328Updated 8 months ago
- Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX☆29Updated last year
- VoXtream is a Full-Stream Zero-shot TTS model with Extremely Low Latency☆174Updated last month
- Examples of using the llasa-tts models locally☆181Updated 7 months ago
- Collection of Open Source Speech Data☆162Updated 2 months ago
- Open Audio Watermarking Tool☆394Updated last week