{"data":{"node":{"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":"Active","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"},"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":"api","name":"api"},{"slug":"api-integration","name":"api integration"},{"slug":"audio-to-text","name":"audio-to-text"},{"slug":"real-time","name":"real-time"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"translation","name":"translation"},{"slug":"windows-11","name":"windows-11"}],"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":"modelscope-funasr","name":"FunASR","tagline":"Industrial-grade speech recognition toolkit","github_url":"https://github.com/modelscope/FunASR","owner":"modelscope","repo":"FunASR","owner_avatar_url":"https://avatars.githubusercontent.com/u/109945100?v=4","primary_language":"Python","stars":19554,"forks":1965,"topics":["asr","audio","chinese","emotion-recognition","funasr","mcp-server","multilingual-asr","openai-compatible-api","paraformer","punctuation","pytorch","real-time-asr","speaker-diarization","speech-recognition","speech-to-text","streaming-asr","transcription","vllm","voice-activity-detection","whisper-alternative"],"archived":false,"github_pushed_at":"2026-07-30T01:45:38+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/modelscope-funasr","markdown_url":"https://www.graphcanon.com/tools/modelscope-funasr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/modelscope-funasr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=modelscope-funasr","shared_categories":["speech-audio"]},{"slug":"jianchang512-pyvideotrans","name":"pyvideotrans","tagline":"Translate video language and embed dubbing & subtitles","github_url":"https://github.com/jianchang512/pyvideotrans","owner":"jianchang512","repo":"pyvideotrans","owner_avatar_url":"https://avatars.githubusercontent.com/u/3378335?v=4","primary_language":"Python","stars":18478,"forks":2281,"topics":["speech-to-text","text-to-speech","video-transition"],"archived":false,"github_pushed_at":"2026-07-24T05:45:00+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/jianchang512-pyvideotrans","markdown_url":"https://www.graphcanon.com/tools/jianchang512-pyvideotrans.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jianchang512-pyvideotrans","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jianchang512-pyvideotrans","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":"funaudiollm-sensevoice","name":"SenseVoice","tagline":"Multilingual speech understanding toolkit with ASR, emotion recognition, and audio event detection.","github_url":"https://github.com/FunAudioLLM/SenseVoice","owner":"FunAudioLLM","repo":"SenseVoice","owner_avatar_url":"https://avatars.githubusercontent.com/u/167062371?v=4","primary_language":"C","stars":8961,"forks":799,"topics":["asr","audio-analysis","audio-event-detection","cantonese","cross-lingual","emotion-detection","funasr","language-identification","llama-cpp","multilingual","multilingual-asr","pytorch","sensevoice","speech-emotion-recognition","speech-recognition","speech-to-text","speech-understanding","transcription","voice-ai","whisper-alternative"],"archived":false,"github_pushed_at":"2026-07-27T14:04:29+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/funaudiollm-sensevoice","markdown_url":"https://www.graphcanon.com/tools/funaudiollm-sensevoice.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/funaudiollm-sensevoice","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=funaudiollm-sensevoice","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":"collabora-whisperlive","name":"WhisperLive","tagline":"A nearly-live implementation of OpenAI's Whisper for real-time voice recognition","github_url":"https://github.com/collabora/WhisperLive","owner":"collabora","repo":"WhisperLive","owner_avatar_url":"https://avatars.githubusercontent.com/u/4499761?v=4","primary_language":"Python","stars":4190,"forks":574,"topics":["dictation","obs","openai","openvino","openvino-intel","rocm","tensorrt","tensorrt-llm","text-to-speech","translation","voice-recognition","whisper","whisper-tensorrt"],"archived":false,"github_pushed_at":"2026-07-27T20:39:23+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/collabora-whisperlive","markdown_url":"https://www.graphcanon.com/tools/collabora-whisperlive.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/collabora-whisperlive","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=collabora-whisperlive","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":"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":"hydropix-translatebookswithllms","name":"TranslateBooksWithLLMs","tagline":"Translate full-length books and documents with preservation of formatting and no file size limits","github_url":"https://github.com/hydropix/TranslateBooksWithLLMs","owner":"hydropix","repo":"TranslateBooksWithLLMs","owner_avatar_url":"https://avatars.githubusercontent.com/u/5154373?v=4","primary_language":"Python","stars":2275,"forks":297,"topics":["docx","epub","gemini","gemini-api","llm","lmstudio","local-llm","localization-tool","mistral","ollama","openai-api","openrouter","poe","srt-subtitles","translation","translation-tool"],"archived":false,"github_pushed_at":"2026-08-09T20:45:07+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/hydropix-translatebookswithllms","markdown_url":"https://www.graphcanon.com/tools/hydropix-translatebookswithllms.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hydropix-translatebookswithllms","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hydropix-translatebookswithllms","shared_categories":[]},{"slug":"digitalphonetics-ims-toucan","name":"IMS-Toucan","tagline":"Controllable and fast Text-to-Speech for over 7000 languages","github_url":"https://github.com/DigitalPhonetics/IMS-Toucan","owner":"DigitalPhonetics","repo":"IMS-Toucan","owner_avatar_url":"https://avatars.githubusercontent.com/u/42207404?v=4","primary_language":"Python","stars":2209,"forks":317,"topics":["deep-learning","pytorch","speech","speech-processing","speech-synthesis","text-to-speech","toolkit","tts"],"archived":false,"github_pushed_at":"2026-01-25T14:45:14+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/digitalphonetics-ims-toucan","markdown_url":"https://www.graphcanon.com/tools/digitalphonetics-ims-toucan.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/digitalphonetics-ims-toucan","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=digitalphonetics-ims-toucan","shared_categories":["speech-audio"]}]}}