ASLP-lab / VoiceSculptorLinks
An instruct text-to-speech solution based on LLaSA and CosyVoice2 developed by the ASLP lab and collaborators.
☆197Updated last week
Alternatives and similar repositories for VoiceSculptor
Users that are interested in VoiceSculptor are comparing it to the libraries listed below
Sorting:
- A large-scale speech corpus introduced in Spark-TTS, built from diverse open-source datasets for training text-to-speech (TTS) systems.☆104Updated 8 months ago
- Inference code for Audiodec-Valle-Wenetspeech4TTS☆50Updated last year
- ☆29Updated 4 months ago
- Official repository for the WenetSpeech-Chuan dataset.☆138Updated 2 months ago
- CosyVoice_DPO_NOTES: Supercharge Your Cosyvoice model with Cutting-Edge DPO Fine-Tuning!☆112Updated 5 months ago
- Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-Step High-Fidelity Audio Generation☆129Updated last week
- The official repository for the paper “NonVerbalSpeech-38K: A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understandi…☆62Updated last month
- The baselines of ARC-Challenge-Interspeech2026☆56Updated last month
- Torch Audio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆63Updated 4 months ago
- A Lightweight and Streaming Zero-Shot Voice Conversion via Mean Flows☆213Updated 3 weeks ago
- Official Repository of Paper: "Emilia-NV: A Non-Verbal Speech Dataset with Word-Level Annotation for Human-Like Speech Modeling"☆83Updated 4 months ago
- X-Talk is an open-source full-duplex cascaded spoken dialogue system framework enabling low-latency, interruptible, and human-like speech…☆164Updated last week
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆239Updated 2 months ago
- ☆110Updated 4 months ago
- VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling☆95Updated last year
- ☆99Updated last week
- Trainging, inference, and testing of the SAC speech codec model.☆93Updated 2 months ago
- ☆170Updated 5 months ago
- TTSAudioNormalizer is a specialized tool for TTS data production, featuring descriptive statistical analysis of audio loudness and loud…☆110Updated last year
- SpeechJudge: Towards Human-Level Judgment for Speech Naturalness (https://arxiv.org/abs/2511.07931)☆49Updated last month
- Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations☆62Updated last year
- This repository contains a series of works on diffusion-based speech tokenizers, including the official implementation of the paper: "TaD…☆72Updated 4 months ago
- The open-source code of UniAudio2.0☆74Updated 4 months ago
- Official code for "EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting"☆107Updated 3 months ago
- Official implementation of YingMusic-SVC.☆112Updated last month
- ☆78Updated 5 months ago
- UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts☆39Updated 7 months ago
- The open source code for SimpleSpeech series☆145Updated last year
- All generative model in one for better TTS model☆74Updated last year
- A Massive Contextual Speech Recognition Benchmark.☆99Updated 5 months ago