#speech-recognition Repositories
206 repositories total
Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS
Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription.
Arabic-first generative speech recognition โ Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference.
Free, open-source AI editing and livestream clipping tool: turn long videos, livestream replays, and podcasts into viral vertical shorts with one click, then post directly to TikTok, Kwai, Bilibili, Xiaohongshu, and WeChat Channels. AI finds highlights and quotable moments, uses comment heat to identify viral segments, automatically adds subtitles, and converts landscape video to vertical. Runs locally with no watermark and no uploads | Free, open-source Opus Clip alternative, 100% local: AI clips long videos and livestream VODs into viral 9:16 shorts for TikTok and YouTube Shorts. No credits, no watermark, no uploads. Windows/macOS/Linux.