Havuz

audio.cpp with a full-task WebUI - pure C++ audio-model inference engine powered by ggml. TTS, ASR/STT, VAD, voice conversion, speaker diari

Qwen Audio Agent, mevcut AI Agents için gerçek zamanlı sesli etkileşimi ve konuşma sürerken arka plan görevleri yürütmeyi sağlayan bir runtime sunuyor.

Neden yükseliyor · 63 günlük yaşına karşılık 2.768 yıldız, son 28 günde 271 commit ve 10 farklı yazar güçlü ilgi ve geliştirme temposuna işaret ediyor. README'de v2.0.0 ile gelen ACP/A2A entegrasyonu ve birleşik orchestration runtime da projenin kapsamının hızla genişlediğini gösteriyor; bu metrikler tek başına üretim olgunluğunu kanıtlamaz.

NeMo-Speech.cpp is a lightweight C++ inference runtime for Speech models

Local voice dictation for mac, windows and linux

把电脑或麦克风声音转成实时翻译字幕。Live translated subtitles from computer or microphone audio.

Open-source voice typing for Windows and macOS — a Wispr Flow / Superwhisper alternative. Press a shortcut, speak, and AI-polished text land

Free offline AI video dubbing studio for Windows — voice cloning, translation, subtitles & on-screen-text localization. 100% local, one nati

Гига Писарь: бесплатная локальная русская диктовка для macOS на GigaAM v3. Зажал правый ⌘, сказал, отпустил. Giga Pisar: offline Russian dic

按课表记好每一节课、被点名时及时提醒的本地优先 Android 课堂助手：离线录音转写、点名提醒、课后回放搜索与可选 AI 答案

A 0.9B model for long-form transcription in 50+ languages with speaker diarization, timestamps, and acoustic event awareness

Lightning-fast, free, local first voice dictation for macOS with on-device transcription

Free, open source voice dictation for macOS. On-device transcription with Apple's Speech framework. No cloud/no API keys/no account.

免费开源的 AI 剪辑 / 直播切片工具:长视频、直播回放、播客一键切成爆款竖屏短视频,直发抖音/快手/B站/小红书/视频号——AI 找高光金句、弹幕热度进爆点判断、自动加字幕、横屏转竖屏,本地运行无水印不上传 | Free open-source Opus Clip alter

日语／英语／中文音视频 → 中文/英文配音与字幕。支持音色克隆、双语混音、RTF 空间处理、人声分离、批量处理和仅字幕导出。JA/EN/ZH media → Chinese/English dubbing & subtitles. Voice cloning, bilingual

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

hayamimi, specialist ASR modellerini dile göre yönlendirerek CPU üzerinde gerçek zamanlı, çok dilli konuşma dökümü ve canlı altyazı sağlar.

Neden yükseliyor · 34 günlük yaşına karşın 348 yıldız ve son 28 günde 112 commit dikkat çekici ilgi ve geliştirme temposuna işaret ediyor. Ancak bu çalışma 3 farklı yazarla sınırlı; ilginin nedenini veya kalıcı benimsemeyi tek başına kanıtlamıyor.

On-device, real-time multimodal AI with features similar to GPT-Live

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

Transcribe any video URL or audio file into plaintext. No GPU. No cloud. One command.

An end-to-end framework for multi-speaker transcription that jointly models who spoke, when, and what.

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

A mental-model-first field guide to Audio AI — from raw waveforms to production voice systems. Covers ASR, TTS, audio classification, Transf

Talk to your Claude Code agent out loud. Hold a key, speak, and it answers in a real voice about a second later, with all its tools and its

The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your o

本地优先 AI 语音输入工具 | Local-first AI voice typing tool. 支持 Whisper/SenseVoice/Parakeet/Qwen asr，离线可用，LLM 智能润色. Open-source speech-to-text with LL

Voice for the Linux desktop: dictation, read-aloud, and voice-driven LLM commands. Wayland & X11: Hyprland, Sway, Niri, GNOME, KDE. Cloud or

ScribeCrate: open-source, self-hosted Whisper speech-to-text server powered by faster-whisper. OpenAI-compatible transcription and English t

Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.

Conversational-AI framework for Go.

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

Linux 原生自适应语音输入：IBus 光标内实时出字、术语纠错与用户自有训练数据。

Fast, local-first dictation for macOS

Kesha listens and talks back: local speech to text and text to speech for agents and scripts, fastest on Apple Silicon.

Local STT server powered by GigaAM v3.

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

离线优先的 Android 输入法：全拼/双拼、离线语音、常用语与剪贴板，数据不出设备 | Offline-first Android IME (librime · sherpa-onnx)

End-to-end subtitle translation workstation with cloud and local OpenVINO model support.

ZeusHammer - AI Super Agent with Local Brain, Voice Interaction & Three-Tier Memory

本地优先的 macOS 与 Windows 语音输入工具，支持端侧 SenseVoice 识别、全局语音输入、文件转写及可选 AI 校对。Local-first voice dictation for macOS and Windows with on-device SenseV

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。

听记 (Tingji) — 本地会议录音转写与纪要，FunASR + LLM，数据不出本机。Local meeting transcription & minutes, runs entirely offline.

Hands-free on-device voice loop for macOS: Apple SFSpeechRecognizer + cloned-voice TTS, continuous listening, zero cloud. Originally built t

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

Word and phoneme level speech timing for spontanoues speech. Fast, accurate and robust.

A macOS voice, screenshot, clipboard, and coding-agent workbench.

Generate degraded speech datasets for noise-robust ASR benchmarking

为 JAV 日语视频生成日文、中文或双语 SRT 字幕。支持本地音视频识别、时间轴对齐及 API 或本地模型翻译；网页界面操作，视频与音频留在本机。适用于 Windows + NVIDIA 显卡。

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

Voice and text control for macOS. One floating bar, live UI action selection with Jev, and a continuous observe–act–verify loop.