Havuz

Live English speech recognition on the ESP32-P4: a 65.7M-parameter streaming transducer in 2/4-bit weights, faster than real time, on the ch

小瑞 / Rui — self-hosted, local-first voice assistant for smart speakers (Xiaomi LX06 via open-xiaoai). FastAPI control plane + local AEC/KWS/

Inference code for Haas, fast and accurate Japanese speech recognition

Reproducible speech-to-text benchmark: WER, latency and cost for Velma, Deepgram, AssemblyAI, Chirp 3, MAI-Transcribe 2, Moonshine and whisp

Speculative Decoding for fast ASR and TTS inference

Free offline AI voice studio for Windows — text-to-speech with cloned and built-in voices, and speech recognition with speakers. Russian don

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

SpeakMore：口述成文，划词即译。开源、免费的语音输入与翻译工具，支持 Mac 与 Windows：语音输入、语音翻译、划词翻译。兼容 Gemini、OpenAI、通义千问、DeepSeek、Kimi、智谱 GLM、MiniMax 及任意 OpenAI 兼容服务，语音输入亦

ASR bridge exposing Weixin voice input as a programmable speech transcription API on Windows

日语、英语视频与直播实时同传悬浮字幕（Android / macOS / Windows）｜本地离线语音识别 · 自备 LLM 翻译（BYOK）

Mynah — self-hosted realtime digital human. One GPU, full admin console, Apache-2.0. 自己服务器上的实时数字人系统

Local-first voice input for macOS (随言). Hold a shortcut, speak, and the text is typed at your cursor. Recognition runs on your Mac with Sens

Local speech-to-text at GPU speed: Parakeet, GigaAM and Whisper in pure Rust, as a library and an ollama-like CLI

Offline speech-to-text on the STM32N6 microcontroller: free English speech recognition on the NPU, no cloud

Streaming Persian (Farsi) speech recognition: fine-tuning NVIDIA Nemotron 3.5 ASR streaming. Data prep, training, evaluation, inference.

Gratis svensk tal-till-text som körs lokalt på din Mac eller Linux-dator. Transkribera intervjuer och möten offline med KB-Whisper och Klang

Oído, ESP32-S3 üzerinde cloud veya NPU olmadan open-vocabulary speech recognition çalıştırmayı hedefleyen C tabanlı bir ASR motorudur.

Neden yükseliyor · Düşük maliyetli bir mikrodenetleyicide open-vocabulary ASR çalıştırma iddiası ve README’de verilen LibriSpeech sonuçları dikkat çekiyor. Repo 1 günlük ve 46 yıldız almış olsa da son 28 gündeki 6 commit’in tek yazardan gelmesi, ilginin henüz bağımsız benimseme veya sürdürülebilir geliştirme kanıtı olmadığını gösteriyor.

Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR,

Push-to-talk voice typing for Windows, macOS, Linux and Android. On-device or cloud speech recognition, AI polish with presets, a dictionary

Optimized ESP32-S3/P4 fully offline speech to text and text to speech system for Micropython and AtomVM, featuring a finetuned STT model for

Streaming speech recognition toolkit: log-mel features, CTC greedy and prefix-beam decoding, transducer-style frame-synchronous emission, fo

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

Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind

Local, identity-aware speech transcription and diarization engine — turns multi-speaker audio into structured, named intelligence, 100% offl

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。

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

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.

DSH 全双工语音插件：流式语音识别入草稿、语音合成按句朗读 + 实时字幕、开口即打断；本地识别免 API Key，可选唤醒词。 · Full-duplex voice plugin for DeepSeek Harness: streaming speech-to-text i

Phone and word timestamp accuracy on human-labeled TIMIT and Buckeye, clean and under reverb, noise, music and babble. Two tracks, forced al

A smarter subtitle studio powered by advanced ASR models. Refine transcripts with AI and custom glossaries, build bilingual subtitles, and e

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

Official Repo for "AgenticASR: Refining Speech Recognition in Real-World Scenarios via an Agentic Approach"

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

All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine

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

AI驯剪 — AI 自动剪辑视频：转写/剪气口/语义动效自动初剪 + 可视化 AI 视频编辑器人工定剪，开源闭环 | AI rough-cut + human final-cut video editing system

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

面向长视频理解与证据分析的 Video Agent 平台，基于 FastAPI、Vue、MySQL、Redis 和 RocketMQ，支持 ASR/OCR 时间轴证据。

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

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

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

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

Local-first Chinese voice typing for macOS — offline ASR, local polishing model, hotwords, and Self-Evolution.

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

audio.cpp, ggml tabanlı ortak bir C++ runtime üzerinden farklı ses modellerinde yerel inference çalıştırmayı sağlayan bir framework’tür.

Neden yükseliyor · 96 günlük yaşına rağmen 3067 yıldızın yanı sıra son 28 günde 272 commit ve 18 farklı yazar görünüyor; bu, README’deki geniş model desteğinin yanında kayda değer bir geliştirme hareketliliğine işaret ediyor. README performans iyileştirmeleri ve yeni model desteği bildiriyor, ancak bu kıyasların bağımsız doğrulaması verilen bilgilerden anlaşılamıyor.

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.

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

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

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

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