Havuz

On-device simultaneous interpretation on Apple Silicon — VoxCPM2 on MLX at the core, streaming TTS in ~170 ms, voice clone, any-pair transla

中文 AI 语音输入工具：按快捷键说话，在任意应用把口述变成去口头语、可分段和结构化的文字；支持用户词典、中文转英文和自选 ASR/LLM。

macOS AI 会议纪要助手，支持麦克风与系统音频录制、实时转录和选择预设提示词生成会议纪要。

Streaming ASR, audio captioning and speech QA over a whisper-style encoder with pluggable LLM backends

Generate degraded speech datasets for noise-robust ASR benchmarking

Self-hosted meeting transcription portal — speech-to-text, speaker diarization, LLM-corrected transcripts, structured summaries and Word min

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

Deploy streaming ASR + TTS on RK3576/RK3588 — 120ms TTS, 52-language ASR, one Docker command

刚说的，在这儿。开源的 macOS 会议记录：本机实时转写，会中整理，会后用你自己的模型出纪要。

VidkNot（影音笔记舱）— 一键从 11+ 自媒体平台（YouTube、B站、抖音、小红书、快手、TikTok、Twitter/X、Instagram、视频号、微博、Vimeo）提取视频笔记：下载音频、双 ASR 交叉校验、LLM 生成结构化笔记，同步到 Obsidian/飞

Production-ready batch inference for Cohere’s Arabic/English ASR model, with optimized Silero VAD, multi-file GPU batching, subtitles, and o

QwenCleo-ASR is the currently State-Of-The-Art (SOTA) open-source model for Egyptian Arabic & code-switching speech recognition Built on Qwe

Taiwanese Hokkien (Taigi) speech-to-text transcriber - MediaTek Breeze-ASR-26 with faster-whisper, tuned for RTX 3050 4GB low-VRAM GPUs. Gra

Public Python SDK, CLI, and MCP server for extracting metadata, text, timed transcripts, media, and supported comments from Douyin, RedNote,

crawl4ai for video & audio — turn any YouTube video, podcast, or recording into clean timestamped markdown, or a verified TTS/STT training d

Streaming on-device speech recognition for Android — NEON-accelerated FastConformer (32M params), cache-aware streaming with 80 ms look-ahea

Accepted at ISCSLP 2026 · Target-level benchmark for raw-input Chinese news TTS pronunciation

Easy access to speech data across 142 African languages for training TTS and ASR models.

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

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

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。

[🔥 ICML2026 🔥 ]A training-free orchestration framework for building interactive omni-modal assistants by composing off-the-shelf modality ex

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

MacOS voice input with ASR transcription, LLM correction, and global hotkeys.