{"data":{"node":{"slug":"funaudiollm-fun-asr","name":"Fun-ASR","tagline":"Fun-ASR-Nano LLM-ASR model supports 31 languages for real-time speech recognition tasks","github_url":"https://github.com/FunAudioLLM/Fun-ASR","owner":"FunAudioLLM","repo":"Fun-ASR","owner_avatar_url":"https://avatars.githubusercontent.com/u/167062371?v=4","primary_language":"C","stars":1449,"forks":141,"topics":["31-languages","asr","audio","audio-language-model","chinese-dialects","fun-asr","fun-asr-nano","funasr","gguf","llama-cpp","llm-asr","multilingual-asr","on-device","pytorch","real-time-asr","speaker-diarization","speech-recognition","speech-to-text","transcription","whisper-alternative"],"archived":false,"github_pushed_at":"2026-07-24T13:50:47+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/funaudiollm-fun-asr","markdown_url":"https://www.graphcanon.com/tools/funaudiollm-fun-asr.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/funaudiollm-fun-asr","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=funaudiollm-fun-asr"},"categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"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":"asr","name":"asr"},{"slug":"audio-language-model","name":"audio-language-model"},{"slug":"multilingual-asr","name":"multilingual-asr"},{"slug":"real-time-asr","name":"real-time-asr"},{"slug":"speaker-diarization","name":"speaker-diarization"},{"slug":"speech-to-text","name":"speech-to-text"}],"edges":[],"neighbours":[{"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":"alphacep-vosk-api","name":"vosk-api","tagline":"Offline speech recognition API","github_url":"https://github.com/alphacep/vosk-api","owner":"alphacep","repo":"vosk-api","owner_avatar_url":"https://avatars.githubusercontent.com/u/26358566?v=4","primary_language":"Jupyter Notebook","stars":15013,"forks":1740,"topics":["android","asr","deep-learning","deep-neural-networks","deepspeech","google-speech-to-text","ios","kaldi","offline","privacy","python","raspberry-pi","speaker-identification","speaker-verification","speech-recognition","speech-to-text","speech-to-text-android","stt","voice-recognition","vosk"],"archived":false,"github_pushed_at":"2026-07-02T20:03:34+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/alphacep-vosk-api","markdown_url":"https://www.graphcanon.com/tools/alphacep-vosk-api.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alphacep-vosk-api","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alphacep-vosk-api","shared_categories":["speech-audio"]},{"slug":"k2-fsa-sherpa-onnx","name":"sherpa-onnx","tagline":"Speech-to-text and related audio processing tools using ONNX with cross-platform support","github_url":"https://github.com/k2-fsa/sherpa-onnx","owner":"k2-fsa","repo":"sherpa-onnx","owner_avatar_url":"https://avatars.githubusercontent.com/u/71431748?v=4","primary_language":"C++","stars":13842,"forks":1596,"topics":["aarch64","android","arm32","asr","cpp","csharp","dotnet","ios","lazarus","linux","macos","mfc","object-pascal","onnx","raspberry-pi","risc-v","speech-to-text","text-to-speech","vits","windows"],"archived":false,"github_pushed_at":"2026-07-29T03:35:02+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/k2-fsa-sherpa-onnx","markdown_url":"https://www.graphcanon.com/tools/k2-fsa-sherpa-onnx.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/k2-fsa-sherpa-onnx","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=k2-fsa-sherpa-onnx","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":"uberi-speech-recognition","name":"speech_recognition","tagline":"Speech recognition module for Python","github_url":"https://github.com/Uberi/speech_recognition","owner":"Uberi","repo":"speech_recognition","owner_avatar_url":"https://avatars.githubusercontent.com/u/437196?v=4","primary_language":"Python","stars":8977,"forks":2415,"topics":["audio","python","speech-recognition","speech-to-text"],"archived":false,"github_pushed_at":"2026-06-16T22:33:12+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/uberi-speech-recognition","markdown_url":"https://www.graphcanon.com/tools/uberi-speech-recognition.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/uberi-speech-recognition","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=uberi-speech-recognition","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":"myshell-ai-melotts","name":"MeloTTS","tagline":"High-quality multi-lingual text-to-speech library by MyShell.ai","github_url":"https://github.com/myshell-ai/MeloTTS","owner":"myshell-ai","repo":"MeloTTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/127754094?v=4","primary_language":"Python","stars":7551,"forks":1059,"topics":["chinese","english","french","japanese","korean","multilingual","spanish","text-to-speech","tts"],"archived":false,"github_pushed_at":"2024-12-24T19:17:13+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/myshell-ai-melotts","markdown_url":"https://www.graphcanon.com/tools/myshell-ai-melotts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/myshell-ai-melotts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=myshell-ai-melotts","shared_categories":["speech-audio"]},{"slug":"mahmoudashraf97-whisper-diarization","name":"whisper-diarization","tagline":"Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper","github_url":"https://github.com/MahmoudAshraf97/whisper-diarization","owner":"MahmoudAshraf97","repo":"whisper-diarization","owner_avatar_url":"https://avatars.githubusercontent.com/u/32404268?v=4","primary_language":"Jupyter Notebook","stars":5615,"forks":503,"topics":["asr","speaker-diarization","speech","speech-recognition","speech-to-text","whisper"],"archived":false,"github_pushed_at":"2026-02-23T15:56:59+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/mahmoudashraf97-whisper-diarization","markdown_url":"https://www.graphcanon.com/tools/mahmoudashraf97-whisper-diarization.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mahmoudashraf97-whisper-diarization","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mahmoudashraf97-whisper-diarization","shared_categories":["speech-audio"]},{"slug":"dograh-hq-dograh","name":"dograh","tagline":"Self-hosted open source voice AI platform","github_url":"https://github.com/dograh-hq/dograh","owner":"dograh-hq","repo":"dograh","owner_avatar_url":"https://avatars.githubusercontent.com/u/191861025?v=4","primary_language":"Python","stars":5064,"forks":1185,"topics":["ai-calling","asterisk-ari","conversational-ai","inbound-calls","local-llm","no-code","on-prem-voice-agent-platform","open-source","open-source-voice-ai","outbound-calls","pipecat","python","self-hosted","speech-to-speech","speech-to-text","telephony","text-to-speech","vapi-alternative","voice-agents","voice-ai-platform"],"archived":false,"github_pushed_at":"2026-07-29T10:51:41+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/dograh-hq-dograh","markdown_url":"https://www.graphcanon.com/tools/dograh-hq-dograh.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/dograh-hq-dograh","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=dograh-hq-dograh","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":"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"]}]}}