Search Results for "form"

...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.

FireRedTTS2 is a next-generation open-source text-to-speech (TTS) system focused on long-form, streaming speech synthesis for multi-speaker dialogue, delivering stable natural speech with context-aware prosody and reliable speaker transitions that support real-time and conversational applications. It features a specialized streaming speech tokenizer and a dual-transformer architecture that enables low latency and high-quality synthesis, making it suitable for interactive systems like chatbots, podcasts, and applications where dynamic turn-taking between speakers is essential. ...

...The project provides a straightforward CLI (mlx_audio.tts.generate) as well as a Python API for programmatic generation of audio, including parameters for voice choice, speed, language hints, output format, and sample rate. It includes examples such as audiobook generation to demonstrate long-form synthesis and joined audio segments. On top of that, MLX-Audio offers a modern web interface powered by FastAPI, with real-time waveform and 3D visualizations, file upload, and audio management.

MetaVoice — in the form of its source repository “metavoice-src” — is a large-scale text-to-speech (TTS) model. Specifically, the base model (MetaVoice-1B) uses around 1.2 billion parameters and has been trained on a massive dataset — reportedly around 100,000 hours of speech data. The goal is to provide human-like, expressive, and flexible TTS: able to generate natural-sounding speech that can handle diverse inputs and likely generalize over voice styles, intonation, prosody, and perhaps multiple languages or accents. ...

...A distinctive feature is the “voice gacha” system, which batch-generates many distinct voice timbres and allows users to save the ones they like into a curated voice library. It has first-class support for long-form audio generation, making it suitable for audiobooks, podcasts, or long narration tasks. The project also implements multi-speaker or role-based reading, letting users assign different voices to different characters in a script and even use a large language model to generate that script in one step.

WaveRNN is a PyTorch implementation of DeepMind’s WaveRNN vocoder, bundled with a Tacotron-style TTS front end to form a complete text-to-speech stack. As a vocoder, WaveRNN models raw audio with a compact recurrent neural network that can generate high-quality waveforms more efficiently than many traditional autoregressive models. The repository includes scripts and code for preprocessing datasets such as LJSpeech, training Tacotron to produce mel spectrograms, training WaveRNN on those spectrograms (with optional GTA data), and finally generating audio. ...