Search Results for "high performance computing"

The OmniVoice project is a cutting-edge multilingual text-to-speech system designed to generate high-quality speech across more than 600 languages. Built on a diffusion language model-style architecture, it combines scalability with strong performance, enabling both natural-sounding voice synthesis and efficient inference speeds. One of its most notable capabilities is zero-shot voice cloning, allowing users to replicate a speaker’s voice using only a short reference audio clip. ...

VoxCPM2 is an advanced open-source text-to-speech system that redefines speech synthesis by eliminating traditional tokenization and instead generating continuous speech representations through a diffusion-based autoregressive architecture. Built on top of the MiniCPM model family, it enables highly natural, expressive, and context-aware speech generation that adapts tone, emotion, and pacing directly from input text. The system is trained on massive multilingual datasets, enabling support...

Qwen3-TTS is an open-source text-to-speech (TTS) project built around the Qwen3 large language model family, focused on generating high-quality, natural-sounding speech from plain text input. It provides researchers and developers with tools to transform text into expressive, intelligible audio, supporting multiple languages and voice characteristics tuned for clarity and fluidity. The project includes pre-trained models and inference scripts that let users synthesize speech locally or...

...Users can train on standard datasets like LJSpeech or plug in their own corpora, with helper tools for computing dataset statistics, extracting phoneme durations, and running multi-GPU training.

...Its architecture follows a token-based, multi-stage pipeline inspired by AudioLM and SPEAR-TTS: Whisper is used to produce semantic tokens, EnCodec compresses the waveform into acoustic tokens, and Vocos reconstructs high-fidelity audio from those tokens. The repository includes notebooks and scripts for inference, long-form synthesis, and finetuning, as well as pre-trained models and converted datasets hosted on Hugging Face. Performance optimizations like torch.compile, KV-caching, and architectural tweaks allow the main model to reach up to 12× real-time speed on a consumer RTX 4090.

DragonianVoice is a C++ inference library that unifies multiple speech synthesis, voice conversion, and singing voice synthesis models under a single, high-performance ONNX-based framework. It focuses on being a reusable native library rather than a full UI product, with bindings for C, C++, and C# so it can be embedded into other applications or engines. The project supports a wide range of model families: TTS models such as Tacotron2, VITS, EmotionalVITS, BERTVits2, GPT-SoVITS, SVC systems like SoVitsSvc (v2/v3/v4), RVC, DiffSvc, DiffusionSvc, FishDiffusion, ReflowSvc, and even singing systems like DiffSinger and related pitch/feature extractors like FCPE and RMVPE. ...

The CSM (Conversational Speech Model) is a speech generation model developed by Sesame AI that creates RVQ audio codes from text and audio inputs. It uses a Llama backbone and a smaller audio decoder to produce audio codes for realistic speech synthesis. The model has been fine-tuned for interactive voice demos and is hosted on platforms like Hugging Face for testing. CSM offers a flexible setup and is compatible with CUDA-enabled GPUs for efficient execution.