Havuz

Windows 线上会议面试助手：多会议平台路由、本地流式语音识别、可选领域模块，并针对金融与会计场景做专项优化。

本地优先的直播精彩切片工作流：Qwen3-ASR 全时间轴转录，Agent 筛选与人工确认，Remotion 9:16 渲染。

Fcitx5 voice input addon — PulseAudio/PipeWire capture, Silero VAD, OpenAI-compatible & Volcengine Doubao streaming ASR, AsrSession architec

Chrome extension that turns video subtitles and tab audio into real-time 3D Chinese Sign Language with local Whisper.

Native macOS push-to-talk dictation app — hold key, speak, release to transcribe and paste text via ChatGPT Web or Groq API; no API key requ

Real-time speech translation with transparent on-screen subtitles. 100% local, no cloud

Whisper-large-v3 fine-tune for Indonesian + Javanese + Sundanese ASR. Lhotse + k2 lattice rescoring pipeline.

Speech-first inference runtime in Rust — TTS / ASR / speech-to-speech / VC / speaker ID / VAD. An ONNX Runtime alternative that loads GGUF &

Tidytalk：Mac 本地语音输入工具。按住说话，松开即可得到整理后的文本。语音识别完全本机运行，可搭配 Ollama 本地大模型润色转写内容，数据不会离开你的电脑。免费开源。| Private on-device voice input for Mac. Hold to s

Live on-device transcription for Zoom and Google Meet calls on macOS. Knows the moment a question ends, then drafts an answer from your own

中英混著講，落下的是乾淨的繁體中文。macOS 選單列語音輸入，whisper.cpp 全程在本機跑，kubectl、Terraform 這類術語內建修正。

Hackable voice AI assistant for Windows: wake it with your voice, bring your own LLM (Claude/Groq/Ollama/OpenAI/Gemini), and it actually doe

Run NVIDIA's tri-modal Nemotron Omni (text+vision+audio) entirely on Apple Silicon — pure MLX runtime, parity-verified against NVIDIA's refe

Local-first personal AI voice assistant for web, Windows, Telegram, Discord, Slack & WhatsApp — Ollama + MCP tools, Fluid Motion audio visua

Local, offline text-to-speech and voice cloning on audio.cpp — multi-voice narration, voice design, sound/music generation, and a real-time

面向杭电「上课啦」的 Windows 课堂辅助工具，支持本地语音识别、关键词提醒与可选签到辅助。

Rust CLI for AI subtitle workflows: transcribe, segment, translate, evaluate, and burn or mux subtitles.

Compare two local Persian (Farsi) speech-to-text models side by side: a Persian Whisper fine-tune vs. general large-v3, on Apple Silicon.

Offline multi-speaker meeting-speech toolkit: planted-ground-truth synthetic meeting factory, VAD, speaker embeddings, diarization (AHC/spec

Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, ben

Hermes Agent TTS and STT plugin for AllModels speech models and voices.

Skill that drives a visual-reconstruction, editable-asset-extraction, 3D, audio, voice and video-generation pipeline from a local Linux cont

Bosnian-first offline assistant: type, speak, and snap street text → English. FastAPI app + Kaggle-trained listen/read models. Fail-stop tra