Search Results for "latency"

VCClient is a real-time voice conversion system that uses machine learning models to transform a speaker’s voice into another voice with minimal latency. It is designed for live applications such as streaming, gaming, and virtual communication, where immediate feedback is essential. The system supports multiple voice conversion models, including RVC and other neural network-based approaches, allowing users to switch between different voices or customize their output. It provides both a graphical user interface and API access, making it suitable for casual users as well as developers who want to integrate voice transformation into their own applications. ...

LiveAvatar is an open-source research and implementation project that provides a unified framework for real-time, streaming, interactive avatar video generation driven by audio and other control signals. It implements techniques from state-of-the-art diffusion-based avatar modeling to support infinite-length continuous video generation with low latency, enabling interactive AI avatars that maintain continuity and realism over extended sessions. The project co-designs algorithms and system optimizations, such as block-wise autoregressive processing and fast sampling strategies, to deliver real-time frame rates (e.g., ~45 FPS on appropriate GPU clusters) while handling non-stop generation without quality degradation. ...

PersonaPlex is an open-source real-time conversational speech AI model that goes beyond traditional text chat by providing full-duplex speech-to-speech interaction, meaning it can listen and talk at the same time instead of waiting for you to finish speaking before responding. This architectural approach eliminates awkward pauses and makes conversations feel much more human-like, with natural behaviors such as overlapping speech, interruptions, and fluent turn-taking, traits that traditional...

...It uses Mimi, a state-of-the-art streaming neural audio codec. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size), yet performs better than existing, non-streaming, codecs like SpeechTokenizer (50 Hz, 4kbps), or SemantiCodec (50 Hz, 1.3kbps). Moshi models two streams of audio: one corresponds to Moshi, and the other one to the user. At inference, the stream from the user is taken from the audio input, and the one for Moshi is sampled from the model's output. ...

SuperBoucle is a loop based software fully controllable with any midi device. SuperBoucle is also synced with jack transport. You can use it on live performance or for composition. SuperBoucle is composed of a matrix of sample controllable with external midi device like pad. SuperBoucle will send back information to midi device (light up led). Sample will always start and stop on a beat or group of beats. You can adjust duration of sample (loop period) in beat and offset in beat. But you...