{"data":{"node":{"slug":"bugbakery-audapolis","name":"audapolis","tagline":"An editor for spoken-word media with automatic transcription.","github_url":"https://github.com/bugbakery/audapolis","owner":"bugbakery","repo":"audapolis","owner_avatar_url":"https://avatars.githubusercontent.com/u/85747362?v=4","primary_language":"TypeScript","stars":1879,"forks":61,"topics":["audio-editing","speech-to-text","transcription","video-editing"],"archived":false,"github_pushed_at":"2026-06-24T10:33:39+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/bugbakery-audapolis","markdown_url":"https://www.graphcanon.com/tools/bugbakery-audapolis.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bugbakery-audapolis","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bugbakery-audapolis"},"categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"audio-editing","name":"audio-editing"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"transcription","name":"transcription"},{"slug":"video-editing","name":"video-editing"}],"edges":[],"neighbours":[{"slug":"systran-faster-whisper","name":"faster-whisper","tagline":"Faster Whisper transcription with CTranslate2","github_url":"https://github.com/SYSTRAN/faster-whisper","owner":"SYSTRAN","repo":"faster-whisper","owner_avatar_url":"https://avatars.githubusercontent.com/u/1520500?v=4","primary_language":"Python","stars":24689,"forks":2006,"topics":["deep-learning","inference","openai","quantization","speech-recognition","speech-to-text","transformer","whisper"],"archived":false,"github_pushed_at":"2025-11-19T14:40:46+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/systran-faster-whisper","markdown_url":"https://www.graphcanon.com/tools/systran-faster-whisper.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/systran-faster-whisper","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=systran-faster-whisper","shared_categories":["speech-audio"]},{"slug":"koljab-realtimestt","name":"RealtimeSTT","tagline":"Realtime speech-to-text library with advanced voice activity detection and wake word activation","github_url":"https://github.com/KoljaB/RealtimeSTT","owner":"KoljaB","repo":"RealtimeSTT","owner_avatar_url":"https://avatars.githubusercontent.com/u/7604638?v=4","primary_language":"Python","stars":10014,"forks":850,"topics":["python","realtime","speech-to-text"],"archived":false,"github_pushed_at":"2026-06-12T20:03:56+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/koljab-realtimestt","markdown_url":"https://www.graphcanon.com/tools/koljab-realtimestt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/koljab-realtimestt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=koljab-realtimestt","shared_categories":["speech-audio"]},{"slug":"modelscope-funclip","name":"FunClip","tagline":"A video transcription and subtitle generation tool with LLM-assisted functionality.","github_url":"https://github.com/modelscope/FunClip","owner":"modelscope","repo":"FunClip","owner_avatar_url":"https://avatars.githubusercontent.com/u/109945100?v=4","primary_language":"Python","stars":6085,"forks":731,"topics":["ai-tools","ai-video-editing","asr","auto-subtitles","chinese","content-creation","funasr","funclip","gradio","llm","paraformer","speech-recognition","speech-to-text","subtitles-generator","transcription","video-editing","video-processing","video-subtitles","video-transcription","whisper-alternative"],"archived":false,"github_pushed_at":"2026-07-29T13:06:47+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/modelscope-funclip","markdown_url":"https://www.graphcanon.com/tools/modelscope-funclip.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/modelscope-funclip","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=modelscope-funclip","shared_categories":["speech-audio"]},{"slug":"denizsafak-abogen","name":"abogen","tagline":"Generate audiobooks from EPUBs, PDFs and text with synchronized captions.","github_url":"https://github.com/denizsafak/abogen","owner":"denizsafak","repo":"abogen","owner_avatar_url":"https://avatars.githubusercontent.com/u/39929354?v=4","primary_language":"Python","stars":5429,"forks":398,"topics":["audiobook","audiobooks","content-creation","content-creator","ebook","epub","epub-converter","kokoro","kokoro-82m","kokoro-tts","llm","media-generation","narrator","speech-synthesis","subtitles","text-to-audio","text-to-speech","tts","voice-conversion","voice-synthesis"],"archived":false,"github_pushed_at":"2026-07-23T13:27:54+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/denizsafak-abogen","markdown_url":"https://www.graphcanon.com/tools/denizsafak-abogen.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/denizsafak-abogen","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=denizsafak-abogen","shared_categories":["speech-audio"]},{"slug":"openwhispr-openwhispr","name":"openwhispr","tagline":"Voice-to-text dictation app with local and cloud models","github_url":"https://github.com/OpenWhispr/openwhispr","owner":"OpenWhispr","repo":"openwhispr","owner_avatar_url":"https://avatars.githubusercontent.com/u/254803777?v=4","primary_language":"JavaScript","stars":5018,"forks":715,"topics":["ai","anthropic","cross-platform","gemini","groq","linux","macos","nvidia","open-source","openai","parakeet","speech-to-text","transcribe","whisper","windows"],"archived":false,"github_pushed_at":"2026-07-30T07:57:27+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/openwhispr-openwhispr","markdown_url":"https://www.graphcanon.com/tools/openwhispr-openwhispr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openwhispr-openwhispr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openwhispr-openwhispr","shared_categories":["speech-audio"]},{"slug":"koljab-realtimetts","name":"RealtimeTTS","tagline":"Converts text to speech in realtime","github_url":"https://github.com/KoljaB/RealtimeTTS","owner":"KoljaB","repo":"RealtimeTTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/7604638?v=4","primary_language":"Python","stars":4002,"forks":399,"topics":["python","realtime","speech-synthesis","text-to-speech"],"archived":false,"github_pushed_at":"2026-05-31T17:07:41+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/koljab-realtimetts","markdown_url":"https://www.graphcanon.com/tools/koljab-realtimetts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/koljab-realtimetts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=koljab-realtimetts","shared_categories":["speech-audio"]},{"slug":"sakirinn-livecaptions-translator","name":"LiveCaptions-Translator","tagline":"Lightweight and powerful real-time audio/speech translation tool","github_url":"https://github.com/SakiRinn/LiveCaptions-Translator","owner":"SakiRinn","repo":"LiveCaptions-Translator","owner_avatar_url":"https://avatars.githubusercontent.com/u/78298057?v=4","primary_language":"C#","stars":3415,"forks":240,"topics":["api","api-integration","audio-to-text","livecaptions","real-time","speech-to-text","translation","windows","windows-11"],"archived":false,"github_pushed_at":"2026-07-22T14:24:35+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/sakirinn-livecaptions-translator","markdown_url":"https://www.graphcanon.com/tools/sakirinn-livecaptions-translator.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sakirinn-livecaptions-translator","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sakirinn-livecaptions-translator","shared_categories":["speech-audio"]},{"slug":"ahmetoner-whisper-asr-webservice","name":"whisper-asr-webservice","tagline":"OpenAI Whisper ASR Webservice API","github_url":"https://github.com/ahmetoner/whisper-asr-webservice","owner":"ahmetoner","repo":"whisper-asr-webservice","owner_avatar_url":"https://avatars.githubusercontent.com/u/3612657?v=4","primary_language":"Python","stars":3311,"forks":580,"topics":["asr","automatic-speech-recognition","docker","openai-whisper","speech","speech-recognition","speech-to-text"],"archived":false,"github_pushed_at":"2025-11-23T20:52:04+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/ahmetoner-whisper-asr-webservice","markdown_url":"https://www.graphcanon.com/tools/ahmetoner-whisper-asr-webservice.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ahmetoner-whisper-asr-webservice","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ahmetoner-whisper-asr-webservice","shared_categories":["speech-audio"]},{"slug":"pluja-whishper","name":"whishper","tagline":"Open-source local audio transcription and subtitling suite with web UI","github_url":"https://github.com/pluja/whishper","owner":"pluja","repo":"whishper","owner_avatar_url":"https://avatars.githubusercontent.com/u/64632615?v=4","primary_language":"Svelte","stars":3048,"forks":179,"topics":["ai","audio-to-text","golang","speech-recognition","speech-to-text","stt","subtitles","sveltekit","transcription","ui","web","web-whisper","webapp","whisper"],"archived":false,"github_pushed_at":"2025-08-15T18:19:02+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/pluja-whishper","markdown_url":"https://www.graphcanon.com/tools/pluja-whishper.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pluja-whishper","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pluja-whishper","shared_categories":["speech-audio"]},{"slug":"open-less-openless","name":"openless","tagline":"AI-polished text from voice input for macOS and Windows","github_url":"https://github.com/Open-Less/openless","owner":"Open-Less","repo":"openless","owner_avatar_url":"https://avatars.githubusercontent.com/u/283287307?v=4","primary_language":"Rust","stars":2881,"forks":252,"topics":["ai-prompt","asr","dictation","linux","llm","macos","open-source","prompt-engineering","rust","speech-to-text","tauri","typeless","typeless-alternative","voice-input","windows","wispr-flow-alternative"],"archived":false,"github_pushed_at":"2026-07-22T00:52:10+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/open-less-openless","markdown_url":"https://www.graphcanon.com/tools/open-less-openless.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/open-less-openless","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=open-less-openless","shared_categories":["speech-audio"]},{"slug":"linto-ai-whisper-timestamped","name":"whisper-timestamped","tagline":"Multilingual Automatic Speech Recognition with word-level timestamps and confidence","github_url":"https://github.com/linto-ai/whisper-timestamped","owner":"linto-ai","repo":"whisper-timestamped","owner_avatar_url":"https://avatars.githubusercontent.com/u/36000254?v=4","primary_language":"Python","stars":2832,"forks":212,"topics":["asr","attention-is-all-you-need","attention-mechanism","attention-model","attention-network","attention-seq2seq","attention-visualization","deep-learning","machine-learning","multilingual-models","python","python3","pytorch","speaker-diarization","speech","speech-processing","speech-recognition","speech-to-text","transformers","whisper"],"archived":false,"github_pushed_at":"2025-09-09T07:04:36+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/linto-ai-whisper-timestamped","markdown_url":"https://www.graphcanon.com/tools/linto-ai-whisper-timestamped.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/linto-ai-whisper-timestamped","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=linto-ai-whisper-timestamped","shared_categories":["speech-audio"]},{"slug":"fluidinference-fluidaudio","name":"FluidAudio","tagline":"CoreML audio models for text-to-speech, speech-to-text, voice activity detection and speaker diarization in Swift.","github_url":"https://github.com/FluidInference/FluidAudio","owner":"FluidInference","repo":"FluidAudio","owner_avatar_url":"https://avatars.githubusercontent.com/u/216957621?v=4","primary_language":"Swift","stars":2554,"forks":360,"topics":["ane","asr","audio","automatic-speech-recognition","avfoundation","coreml","ios","macos","nvidia","parakeet","real-time","speaker-diarization","speaker-embedding","speaker-identification","speaker-recognition","speech-to-text","swift","vad","voice-activity-detection"],"archived":false,"github_pushed_at":"2026-07-26T00:49:55+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/fluidinference-fluidaudio","markdown_url":"https://www.graphcanon.com/tools/fluidinference-fluidaudio.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fluidinference-fluidaudio","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fluidinference-fluidaudio","shared_categories":["speech-audio"]}]}}