Voice & audio

Speech-to-text & transcription

381 agents · most starred first

Speech-to-text & transcription, page 3 of 4

wechat-video-subtitle★ 10

下载微信视频号普通视频、直播回放并转写逐字稿的 AI Agent Skill

heypip★ 10

A tiny friend in your Mac's notch that listens to your calls and whispers what to say. Live transcription on your Mac + your AI agent.

memoflow★ 10

Interactive recording transcription skill with Codex and Qwen-Audio 3.1. Word, Excel and Markdown transcript drafts; self-learning personalized minutes generation skill is planned. 结合 Codex 与阿里云百炼 Qwen-Audio 3.1,交互式转写录音并生成 Word、Excel、Markdown 校对稿skill;个性化纪要生成与反馈学习skill正在开发中。

openai-chatterbox★ 9

A sample Nuxt 3 application that listens to chatter in the background and transcribes it using the powerful OpenAI Whisper, an automatic speech recognition (ASR) system.

Web-Interface-for-NVIDIA-NeMo★ 9

This repository contains an attempt to utilize the NeMo toolkit created by NVIDIA

Dictator-Speech-to-Text★ 9

🎙️ Lightweight macOS menubar app for voice-to-text dictation using OpenAI Whisper API. Hold-to-record with Fn key, instant transcription, auto-paste. Built with Hammerspoon.

whisper-run★ 9

Faster Whisper with Speaker Diarization

py-transcriptor-ai★ 9

PyTranscriptorAi - Transcript videos to text with Ai and add subtitles - OpenAi

oxiwhisper★ 9

Pure Rust Whisper speech-to-text inference engine. Zero C/C++ dependencies.

soenneker.libraries.whisper.ctranslate★ 9

The Whisper_CTranslate2 Windows executable, updated daily

xiaoyuzhou-podcast★ 9

Xiaoyuzhou podcast fetcher & transcriber — download, transcribe with faster-whisper, summarize

Diariz★ 9

Self-hosted, multi-user transcription platform: record or upload audio. Speaker-labeled, timestamped transcripts, Recognize speakers across recordings, Summarize, extract action items and chat over your transcripts with your own OpenAI-compatible LLM. Your Audio, your Server, your Model. Tested: Laptop RTX4070, RTX3090, RTX5090 and ROCM Strix Halo

echoo★ 9

Echoo - A macOS application that saves you hours by stopping context switching.

Whisper_Azure★ 8

An Azure function who convert mp3 audio file into a text file on Azure cloud Storage

multilingual-record-app★ 8

Demo Multilingual Near Real-Time Transcriber

Voice2Text★ 8

Descrição automática de mensagens de voz em conversas privadas no Telegram

mac-speech-to-ai-to-text★ 8

A macOS menu bar app that turns speech into refined, ready-to-send text anywhere you type — powered by local Whisper transcription and AI cleanup.

speech-to-text★ 8

Speech to Text Transcription using OpenAI Whisper v3 and FastAPI

Audiogram★ 8

An app that converts your audio snippets into shareable & engaging Audiogram, customized your way

livekit-whisper★ 8

Livekit STT plugin for openAI whisper models with faster-whisper backend

polished-recognition★ 8

A voice keyboard for Android powered by your own AI — dictate, and polished text appears. Bring your own OpenAI-compatible STT + LLM.

genpark-voice-transcriber★ 8

Real-time audio-to-text with semantic cleanup.

live-subtitles-rokid-ar★ 7

通过Rokid AR眼镜和OpenAI Whisper实现现实生活中的字幕

whisper-tamil★ 7

gradio region:us

transcript-generator★ 7

gradio mcp-server-track speech-to-text whisper groq transcript api stt

suflyor★ 7

Native Rust and Slint meeting overlay for Windows and Apple Silicon macOS, with real-time transcription and local or cloud AI answers.

Vexa-Dashboard★ 6

Open-source web dashboard for Vexa – manage meeting transcriptions, view real-time transcripts, and chat with your meetings using AI.

EchoMind★ 6

An intelligent audio analysis tool that automatically transcribes and enables semantic search of audio recordings using Whisper and LangChain.

enzo★ 6

Enzo, an AI assistant that lives in your Mac's notch. Talk instead of typing, let it take the notes in your meetings, and ask it anything about your work.

MEET-AI-PLATFORM-POWERED★ 5

End-to-end AI-powered video call application where you implement real-time calls with customized AI agents, generate automatic summaries and transcriptions through background processes, and create a post-call experience with video playback, transcript search, and a contextual AI chat. The project also covers authentication, subscriptions, etc

vibe-stt-server★ 5

Speech-to-Text transcription service backed by Whisper

video-audio-to-text★ 5

A Python tool that transcribes video and audio files to text using Whisper, with ChatGPT-powered summarization

transcript-video★ 5

A PowerShell script that automatically generates subtitles in bulk for video files using whisper-ctranslate2.

transcriptr★ 5

Transcriptr is a modern web application that converts audio files to text using artificial intelligence. It provides a clean, intuitive interface for uploading audio files and receiving high-quality transcriptions powered by Replicate's Incredibly Fast Whisper model.

prj-voca-ai★ 5

Transforme áudios do WhatsApp em prompts estruturados prontos para qualquer LLM.

WhisperMe-Audio-Transcriber★ 5

The Ultimate OpenSource Transcription Service made using OpenAI's Whisper-1 Model | Built for the mission : "Accessible AI Education and Technology for all"

speech-to-clipboard★ 5

A simple UI tool written in Python, for recording audio from a microphone and automatically transcribing the recording using OpenAI's Whisper model via OpenAI's API.

videowise★ 5

VideoWise is a video transcription and AI-powered analysis tool that helps users easily upload, transcribe, and interact with video content. Using WhisperX for high-quality transcriptions and Ollama for AI-driven insights, VideoWise makes it easy to search, analyze, and export video data.

aftertalk★ 5

Fully offline iPhone meeting memory. Zero network calls, no Wi Fi required. Records, transcribes, summarises, and answers questions entirely on device. Audio, transcripts, summaries, embeddings, and chat never leave the phone.

whisperforge★ 5

WhisperForge is a Python tool that leverages OpenAI's Whisper model to transcribe large audio files. It automatically splits files into manageable chunks, processes them, and combines the transcriptions into a single document. Ideal for handling lengthy recordings and generating clear, organized transcriptions.

dysub★ 5

An open-source tool to extract subtitles (.srt/.vtt) from Douyin video links via OpenAI-compatible ASR APIs. Supports batch processing and 1-click Docker deployment.

Phi-4-multimodal-instruct-ko-asr★ 5

transformers safetensors phi4mm text-generation automatic-speech-recognition custom_code

whisper-realtime-echo★ 5

real-time and file-based speech-to-text desktop app powered by OpenAI Whisper with a modern Flet GUI

voxpen-desktop★ 5

VoxPen Desktop (語墨) — System-tray voice-to-text app. Global hotkey → dictate → auto-paste. Tauri v2 + Rust + React. BYOK.

omri★ 5

Native macOS/iOS voice dictation and transcription with on-device Nemotron/Apple or BYO Groq/OpenAI

echotype★ 5

🎤 Chrome extension for universal voice dictation powered by ChatGPT Whisper. Copy speech-to-text results anywhere with global keyboard shortcuts. Multi-language, auto-copy, history support.

HeySpeaky★ 5

Background dictation for Windows that survives switching language mid-sentence. Hold Ctrl+Alt, talk, and the text lands in whatever you were typing in.

EchoWave★ 5

Self-hosted AI audio analysis & knowledge workspace for transcription, speaker/emotion review, business insights, and RAG.

skills★ 5

Transcribe audio from your coding agent — the Agent Skill, CLI, and SDK for OpenTranscription.

voiceinput★ 5

Add dictation to any React input or textarea

voice-to-text★ 5

Free offline dictation app for macOS. Push-to-talk voice input for Claude Code, Codex, and any app. Runs 100% locally on the Apple Neural Engine.

aftertalk★ 5

Private Offline AI Meeting Memory

mywisper★ 5

Private, local-first dictation for macOS — global-hotkey speech-to-text powered by Whisper (whisper.cpp + Metal), with optional cloud & AI post-processing.

ezspeak★ 5

Desktop app that records from a global hotkey and pastes speech-to-text using the OpenAI Whisper API or a local whisper.cpp binary. Electron. https://ezspeak.app

sonora★ 5

Sonora - real-time speech-to-text desktop app. Cloud or local models, global hotkey, live streaming, pastes at your cursor. Built with Tauri + Svelte + Rust.

whisper-audiosocket-stt-asterisk★ 5

WASA is an AI-powered transcription, translation and synthesis tool for voiceovers with independent channel control.

stealth★ 5

Open-source native macOS meeting copilot (Cluely-style): real-time two-sided transcription + AI reply suggestions in a screen-share-invisible overlay. Swift/SwiftUI + OpenAI Realtime API. No Electron, no backend.

SpeakIt★ 5

Background dictation for Windows that survives switching language mid-sentence. Hold Ctrl+Alt, talk, and the text lands in whatever you were typing in.

bangla-speech-to-text-benchmark★ 5

Open benchmark of 8 Bengali speech-to-text APIs (Sarvam, Soniox, Deepgram, Google Gemini & Chirp 2, ElevenLabs, OpenAI, Groq Whisper) on 1,001 real Bangla audio clips across 13 domains. Batch + streaming: CER, WER, latency and cost. By Riverborn.

KillerSubtitles★ 5

TikTok-style animated subtitle generator for video. Transcribes with OpenAI Whisper, burns in bold outlined subtitles with word-by-word highlighting. CLI tool with bundled FFmpeg -- zero system dependencies.

Python-Voice-Order★ 4

An project that can transfer your voice order into word command.

audio-capture-n8n★ 4

🎤 Transform any browser tab into an intelligent audio recording system with automated transcription and AI analysis via n8n. Works with Zoom, Meet, Teams, YouTube, Spotify, Discord & more!

advanced-speech-transcription★ 4

A minimalistic yet powerful voice transcribing app that features precise and dynamic speech recognition.

parrot★ 4

Parrot is a Chrome extension that streamlines the note-taking process during work calls. It captures audio, transcribes it using OpenAI's Whisper model, and uses GPT to generate concise notes, which are then uploaded to a specified Notion page.

meetingmind★ 4

MeetingMind — agent-native meeting notes: local recording + whisper.cpp (or your own ASR) transcription, summarized by your terminal agent. macOS, no UI, no cloud.

smart-meeting-assistant★ 4

“拼好会”是一款基于RAG的智能会议辅助系统,支持实时语音识别、英文会议翻译、会议纪要生成与 AI 辅助发言。系统可同时捕获电脑音频与麦克风输入,对会议内容进行低延迟流式识别,并结合RAG技术检索导入的 PDF、PPT、Word 等会议资料,为用户提供上下文相关的发言建议与内容总结。 项目支持 OpenAI、DeepSeek、Gemini、Qwen 等多种大模型,可用于英文会议、学术讨论、项目汇报等场景,帮助用户“听会、记会、翻译会”,提升线上会议效率与信息整理能力。

listen-wise★ 4

Save the last 30 seconds of audio to text using ai. Send that text to a notion page, readwise, obsidian, or just save it locally in a text file.

STT-Grammar-Checker★ 4

gradio region:us

Whisper-gpt-voicescribe★ 4

gradio region:us

Urdu-STT-with-GPT-OSS★ 4

gradio region:us

openai-whisper-api★ 4

A sample speech transcription app implementing OpenAI Text to Speech API based on Whisper, an automatic speech recognition (ASR) system, built using Next 13, the React framework

Speech-to-Text★ 4

This is a Speech to text project which uses openAI's Whisper model.

395-transcribing-with-artificial-intelligence★ 4

In this episode, we look at creating an audio transcription service which allows files uploaded from Active Storage to be transcribed with Artificial Intelligence. However, there are a lot of considerations around the approach from both a performance and thread safety perspectives.

meetwit★ 4

Privacy-first, local-first AI meeting assistant for macOS & Windows — live transcription, an in-meeting copilot grounded in your own documents, and summaries. Everything runs on your machine. No cloud, no telemetry.

voice-message-transcriber★ 3

An iOS share-action extension that transcribes voice messages using Google Cloud Speech API and displays the result instantly as a notification.

ffvoice-engine★ 3

Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用

sonote★ 3

AI 에이전트를 위한 소리 노트 — 실시간 한국어 음성 전사 CLI

EchoSynth★ 3

An audio processing agent that transforms spoken content into polished text and visual representations.

IA-notetaking★ 3

A privacy-first AI meeting assistant that lives as a floating widget on your desktop. Records microphone and system audio natively — Powered by Tauri v2, WhisperX, and LangGraph. Open-source, no bots, no meeting links — then transcribes and summarizes with your LLM of choice, fully local if you want.

one-key-input★ 3

Hold a key, speak, get context-aware AI-polished text typed at your cursor. Windows native, BYO Azure/OpenAI keys, MIT.

Meeting-AI-CC_GLM-CODEX★ 3

AI 会议助手:实时语音转写 + 语句拆分/翻译 + AI 分析的轻量级 Web 应用(Vue 3 + NestJS).Meeting AI assistant: real-time transcription, segmentation/translation, and AI insights (Vue 3 + NestJS).

verbatim-flow★ 3

Capture macOS dictation accurately without rewriting your words, keeping your input true to what you speak and avoiding common app issues.

AUDIO-TO-TEXT-AGENT1★ 3

gradio region:us

real-time-transcriber★ 3

gradio region:us

studio_V1_4_asr_GPT★ 3

gradio region:us

ai-audio-assistant-ui★ 3

AI 音视频助手前端:支持文件与 YouTube 内容导入、ASR 转写、结构化摘要和实时任务进度。

SKAZ★ 3

A macOS desktop app that listens along to lectures and meetings: live speech-to-text, timestamped answers about what you missed, and editable notes next to the transcript

askGPT★ 2

AskGPT is a real-time AI assistant that enhances your calls, interviews, meetings, and lectures by providing instant AI-generated insights. It captures live audio, transcribes speech into text, and generates context-aware responses—all in real-time!

SlasshyWispr★ 2

Desktop voice dictation + AI assistant with online, offline, and hybrid runtimes. Speak, transcribe, rewrite, and respond fast with local Parakeet STT and Ollama support.

open-meet-sum★ 2

Open Meet Sum is an AI assistant for physical meetings that automatically transcribes, summarizes, and analyses audio with human-in-the-loop collaboration. It's a self-hosted solution, supporting both local, model API endpoints and built-in transcription engines.

Voice_To_Summary_Meeting_Assistant★ 2

streamlit region:us

task2_speaker_tagging_leaderboard★ 2

gradio region:us

Post-ASR-N-Best-Text-Speech-Emotion-Recognition★ 2

gradio region:us

agent-meeting-notes★ 2

Discord meeting bot: local Whisper transcription, LLM summarization, and an agent that tracks tasks/decisions as searchable memory across meetings.

AgenticASR-Refiner★ 2

transformers onnx safetensors llama text-generation conversational

transcription-agent-go★ 2

Agentic audio transcription in Go: fast speech-to-text with parallel chunking, an LLM judge agent that compares and merges candidate transcripts, extensible via Agent Skills.

VideoCaptionWhisper★ 1

gradio region:us

Audiototext★ 1

gradio region:us

AI-Speech-Analysis-App-RAG★ 1

gradio region:us

whisper-gpt★ 1

gradio region:us

More in Voice & audio