FlowMirror-HydraVox — A natively accelerated multi-head autoregressive TTS system derived from CosyVoice 3.0. It predicts multiple tokens per step for faster, high-quality speech synthesis, featuring a WebUI, FAST API, and full training pipeline compatible with CosyVoice.
☆49Feb 17, 2026Updated 8 months ago
Alternatives and similar repositories for FlowMirror_HydraVox
Users that are interested in FlowMirror_HydraVox are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Inference for the STFT-VAE continuous audio codec (24kHz, 3.125Hz latent)☆48Jul 12, 2026Updated 3 months ago
- Scaled diffusion transformer for text-to-speech synthesis (DiT + T5Gemma2 conditioning, TorchTitan & Megatron backends, tested up to 1024…☆25Mar 29, 2026Updated 7 months ago
- ☆35Sep 6, 2025Updated last year
- This repository implement a novel zero-shot TTS framework, named Flamed-TTS, focusing on the efficient generation and dynamic pacing in …☆57Aug 9, 2025Updated last year
- ☆52Apr 27, 2026Updated 6 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- poorman's ar-dit tts☆45Dec 31, 2025Updated 10 months ago
- Unified Audio Scene Generation☆13Aug 21, 2026Updated 2 months ago
- Official code for "GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech Mo…☆47Aug 11, 2026Updated 2 months ago
- ☆19Aug 13, 2026Updated 2 months ago
- Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation☆78Jun 16, 2026Updated 4 months ago
- [ACMMM'2024] Generative Expressive Conversational Speech Synthesis☆45Oct 28, 2024Updated 2 years ago
- Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-Step High-Fidelity Audio Generation☆153Mar 8, 2026Updated 7 months ago
- The inference and trainging code for WordVoice.☆75Aug 21, 2026Updated 2 months ago
- 2024 Latest laughter detection & segmentaion model. Paper: "Robust Laughter Segmentation with Automatic Diverse Data Synthesis", Interspe…☆66Sep 1, 2024Updated 2 years 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 repository for NVMOS: Non-Verbal Vocalization Quality Assessment in Speech☆26Jun 16, 2026Updated 4 months ago
- [INTERSPEECH 2025 Oral]Official code for "Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment"☆68Jun 16, 2025Updated last year
- Unofficial PyTorch implementation of "Autoregressive Speech Synthesis without Vector Quantization (MELLE)"☆41Jun 28, 2025Updated last year
- ☆43Nov 18, 2025Updated 11 months ago
- [ICASSP 2026] Task Vector in TTS: Toward Emotionally Expressive Dialectal Speech Synthesis☆43Dec 24, 2025Updated 10 months ago
- Implementation of the paper "Variable Bitrate Residual Vector Quantization for Audio Coding"☆11Apr 10, 2025Updated last year
- ☆114Jul 15, 2026Updated 3 months ago
- [ACL 2026] VoxMind: An End-to-End Agentic Spoken Dialogue System☆46Jul 8, 2026Updated 3 months ago
- [INTERSPEECH 2026] Pre-training, SFT, DPO and GRPO for Text-to-Audio Generation☆51Apr 17, 2026Updated 6 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.
- 5Hz Deep-Compression Speech VAE for AR-Diffusion and CALMs☆56Nov 19, 2025Updated 11 months ago
- ☆30Oct 20, 2026Updated 2 weeks ago
- M5-TTS is a lightweight 50M-parameter TTS language model supporting real-time CPU inference, multilingual and multi-dialect synthesis, ze…☆25Updated this week
- Evaluation code for the Interspeech publication "Towards Frame-level Quality Predictions of Synthetic Speech". Evaluate frame-level repre…☆14Aug 15, 2025Updated last year
- end-to-end text to audio scene generation model☆53Jun 16, 2026Updated 4 months ago
- FlashCosyVoice: A lightweight vLLM implementation built from scratch for CosyVoice.☆252Feb 25, 2026Updated 8 months ago
- （WIP）long form speech generatoins☆30Apr 2, 2025Updated last year
- EMNLP 2026 | Official Repository of UltraVoice☆67Aug 30, 2026Updated 2 months ago
- A large-scale speech corpus introduced in Spark-TTS, built from diverse open-source datasets for training text-to-speech (TTS) systems.☆119May 5, 2025Updated last year
- 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.
- ☆27Jan 27, 2026Updated 9 months ago
- DEX-TTS: Diffusion-based EXpressive TTS with Style Modeling on Time Variability☆108Jan 17, 2025Updated last year
- Official implementation of ACL'26 (findings) paper WESR (Word-level Event-Speech Recognition): A comprehensive benchmark and baseline for…☆48Jan 30, 2026Updated 9 months ago
- Speech Resynthesis and Language Modeling☆27Jun 11, 2025Updated last year
- Official Repository of Paper: "SynParaSpeech: Automated Synthesis of Paralinguistic Datasets for Speech Generation and Understanding" (IC…☆72Apr 27, 2026Updated 6 months ago
- [ACL 2025] OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching☆45Feb 9, 2025Updated last year
- ☆84Apr 28, 2026Updated 6 months ago