This repository is maintained by the Speech Team at Alibaba’s Tongyi Lab, serving as an open-source platform for our cutting-edge research in speech, audio, NLP technologies. We believe in accelerating scientific progress through transparent collaboration, and invite the global research community to explore, reproduce, and build upon our work.
☆60Sep 18, 2026Updated this week
Alternatives and similar repositories for FunResearch
Users that are interested in FunResearch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- NVV-SuperBench: Beyond Words, Beyond Quality—Benchmarking Nonverbal Vocalizations in Speech Generation (Interspeech 2026 long paper)☆19Jun 21, 2026Updated 3 months ago
- A simple implementation for improving CosyVoice2 by GRPO method☆39May 5, 2026Updated 4 months ago
- Lightweight streaming Voice Activity Detection (VAD) tool with ONNX runtime☆24Mar 18, 2026Updated 6 months ago
- [ACL 2026 Main] Open-Ended Speaking Style Modeling via Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training☆107Apr 6, 2026Updated 5 months ago
- The dataset construction pipeline for WordVoice-5A☆19Jul 17, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆32Mar 27, 2026Updated 5 months ago
- Generate a complete audio clip with music, intelligible speech, and sound effects from text in one pass.☆46May 27, 2026Updated 3 months ago
- Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation☆75Jun 16, 2026Updated 3 months ago
- end-to-end text to audio scene generation model☆52Jun 16, 2026Updated 3 months ago
- ☆33Sep 15, 2025Updated last year
- ☆40Apr 3, 2025Updated last year
- Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-Step High-Fidelity Audio Generation☆149Mar 8, 2026Updated 6 months ago
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆253Feb 25, 2026Updated 6 months ago
- ☆112Jul 15, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- WavReward: Spoken Dialogue Models With Generalist Reward Evaluators☆57May 15, 2025Updated last year
- FlowMirror-HydraVox — A natively accelerated multi-head autoregressive TTS system derived from CosyVoice 3.0. It predicts multiple tokens…☆49Feb 17, 2026Updated 7 months ago
- ☆52Apr 27, 2026Updated 4 months ago
- EMNLP 2026 | Official Repository of UltraVoice☆67Aug 30, 2026Updated 3 weeks ago
- [AAAI 2026 oral] KALL-E:Autoregressive Speech Synthesis with Next-Distribution Prediction☆43Sep 25, 2025Updated 11 months ago
- ☆111Oct 16, 2025Updated 11 months ago
- SpeechJudge: Towards Human-Level Judgment for Speech Naturalness (https://arxiv.org/abs/2511.07931)☆84Dec 23, 2025Updated 9 months ago
- 5Hz Deep-Compression Speech VAE for AR-Diffusion and CALMs☆57Nov 19, 2025Updated 10 months ago
- M7-TTS: A Mini-Scale Multilingual and Multi-Dialect Text-to-Speech Language Model with Mimi codec and Multi Token Prediction☆20Mar 19, 2026Updated 6 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- SLMTokBench for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"☆37Aug 29, 2023Updated 3 years ago
- Codebase for 'Scaling Rich Style-Prompted Text-to-Speech Datasets'☆166Mar 26, 2026Updated 5 months ago
- For audio visualization and playback in Jupyter notebooks.☆19Aug 27, 2026Updated 3 weeks ago
- 最棒的的ASR后处理热词方案，基于音素编辑距离，实现热词替换。☆69Jun 10, 2026Updated 3 months ago
- A curated list of models, benchmarks, tools and guides for audio editing☆46Updated this week
- Streamable Text-to-Speech model using a language modeling approach, without vector quantization☆109May 20, 2025Updated last year
- [NeurIPS' 25] Benchmark for evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges.☆232Dec 9, 2025Updated 9 months ago
- Unified Speech Language Model for paper "SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models"(ICLR 2024)☆152Sep 14, 2023Updated 3 years ago
- ☆30May 21, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ESLTTS dataset☆16Feb 6, 2025Updated last year
- Model configurations for scaling SE models in the paper "Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enha…☆44Aug 7, 2024Updated 2 years ago
- The official repository for the paper “NonVerbalSpeech-38K: A Scalable Pipeline for Enabling Non-Verbal Speech Generation and Understandi…☆71Dec 26, 2025Updated 8 months ago
- [ACM Multimedia 24]The official repository of SpeechCraft dataset, a large-scale expressive bilingual speech dataset with natural languag…☆202Feb 28, 2026Updated 6 months ago
- ☆453Mar 25, 2026Updated 5 months ago
- semantic tokenizer for speech and music☆20Jul 6, 2025Updated last year
- KVAE-Audio: a continuous full-band audio waveform autoencoder☆123Aug 10, 2026Updated last month