Fork with streaming inference support + ~6× faster inference
☆256Jun 3, 2026Updated last month
Alternatives and similar repositories for Qwen3-TTS-streaming
Users that are interested in Qwen3-TTS-streaming are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Real-time streaming TTS for Qwen3-TTS with two-phase latency, Hann crossfade, and torch.compile + CUDA graphs optimizations☆93Feb 21, 2026Updated 5 months ago
- Qwen3-TTS with nano vLLM-style optimizations for fast text-to-speech generation. Achieved 3x faster☆135Mar 3, 2026Updated 4 months ago
- Real-time text-to-speech with Qwen3-TTS☆1,261Jul 17, 2026Updated last week
- High-performance Qwen3-TTS implementation | Instruction-driven · Zero-shot voice cloning · Streaming · RTF 0.55☆66Jun 26, 2026Updated last month
- FlowMirror-HydraVox — A natively accelerated multi-head autoregressive TTS system derived from CosyVoice 3.0. It predicts multiple tokens…☆49Feb 17, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- faster inference☆27Jan 20, 2025Updated last year
- Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streamin…☆12,672Mar 17, 2026Updated 4 months ago
- One command to start a streaming ASR server.☆12Oct 2, 2024Updated last year
- Inference for the STFT-VAE continuous audio codec (24kHz, 3.125Hz latent)☆43Jul 12, 2026Updated 2 weeks ago
- ☆212Jun 2, 2026Updated last month
- [ICASSP 2026] Official code for "Measuring Prosody Diversity in Zero-Shot TTS: A New Metric, Benchmark, and Exploration"☆17Apr 16, 2026Updated 3 months ago
- LEMAS‑TTS is a multilingual zero‑shot text‑to‑speech system, supporting 10 languages: Chinese English Spanish Russian French German Ital…☆101Mar 31, 2026Updated 3 months ago
- [INTERSPEECH 2026] Pre-training, SFT, DPO and GRPO for Text-to-Audio Generation☆48Apr 17, 2026Updated 3 months ago
- Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streamin…☆218Jul 10, 2026Updated 2 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- CosyVoice_DPO_NOTES: Supercharge Your Cosyvoice model with Cutting-Edge DPO Fine-Tuning!☆126Aug 8, 2025Updated 11 months ago
- poorman's ar-dit tts☆45Dec 31, 2025Updated 6 months ago
- Zero-shot voice cloning text-to-speech (TTS) with explicit emotion class conditioning built on F5-TTS☆40Mar 3, 2026Updated 4 months ago
- A curated list of models, benchmarks, tools and guides for audio editing☆35Jul 7, 2026Updated 3 weeks ago
- 使用vllm加速cosyvoice2的推理☆498Apr 26, 2025Updated last year
- A unified tokenizer that is capable of both extracting semantic information and enabling high-fidelity audio reconstruction.☆145Sep 19, 2025Updated 10 months ago
- [ACL 2026 Main] Training, inference, and testing of the SAC speech codec model.☆108Nov 1, 2025Updated 8 months ago
- Easy fine-tuning for Qwen3-TTS: Fast voice cloning and high-quality multilingual speech synthesis.☆115May 29, 2026Updated 2 months ago
- A simple implementation for improving CosyVoice2 by GRPO method☆39May 5, 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.
- Official implementation of the paper "BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec"☆218Sep 19, 2024Updated last year
- 最极速的Qwen3-TTS推理方案。将 Qwen3-TTS 的 LLM 部分导出为 GGUF，用 llama.cpp 进行加速推理。后者支持 Vulkan 和 Cuda 加速。☆168Jun 11, 2026Updated last month
- [ICASSP 2026] Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis☆40Dec 24, 2025Updated 7 months ago
- ☆23Oct 17, 2024Updated last year
- Streaming Vocos☆31Jun 10, 2025Updated last year
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆250Feb 25, 2026Updated 5 months ago
- Official repo for CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations☆67Jan 16, 2025Updated last year
- Interact privately with your documents using the power of GPT, 100% privately, no data leaks☆10May 22, 2023Updated 3 years 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 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆42Nov 18, 2025Updated 8 months ago
- An All-in-One Speech, Sound, Music Codec with Single Nested Codebook☆28Oct 11, 2025Updated 9 months ago
- ☆555Apr 3, 2026Updated 3 months ago
- DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action☆114May 20, 2026Updated 2 months ago
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆521Dec 22, 2025Updated 7 months ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆115Updated this week
- ☆43Jun 3, 2026Updated last month