Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

Speed and samples benchmark: for all types of text to speech (TTS) models on Windows/Linux/Mac.

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Official Code for "Rethinking Diffusion Model in High Dimension"

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

Modern Scala 3 client for Redis and Valkey, native and multi-backend

FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3

Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles.

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Safe direct-style streaming, concurrency and resiliency for Scala on the JVM

Deterministic, AI-driven development flows.

Open-source speech AI models from KRAFTON, including Raon-Speech and Raon-SpeechChat for speech understanding, generation, and real-time full-duplex conversation.

Official implementation of AsymFlow, pi-Flow, GMFlow

Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation.

First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come …

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

Warp is an agentic development environment, born out of the terminal.

High-Quality Voice Cloning TTS for 600+ Languages

A Java port of ratatui — build rich terminal UIs from Java

Simple, beautiful CLI output

The first continuous diffusion language model that rivals discrete counterparts on standard language modeling benchmarks like LM1B and OpenWebText.

The open source coding agent.

Hearth fire starter - incubator/dogfooding for Hearth-based macro libraries