{"data":{"node":{"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":2781,"forks":421,"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":"2026-09-20T05:28:22+00:00","maintenance_label":"Very active","stars_delta_30d":227,"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"},"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":"ane","name":"ane"},{"slug":"asr","name":"asr"},{"slug":"audio","name":"audio"},{"slug":"automatic-speech-recognition","name":"automatic-speech-recognition"},{"slug":"avfoundation","name":"avfoundation"},{"slug":"coreml","name":"coreml"},{"slug":"ios","name":"ios"},{"slug":"macos","name":"macos"}],"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":20433,"forks":2039,"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":"2026-09-20T02:15:56+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":15137,"forks":1759,"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":"2026-08-09T13:35:47+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":14860,"forks":1708,"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":"2026-09-20T07:00:27+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":"huggingface-speech-to-speech","name":"speech-to-speech","tagline":"Build local voice agents with open-source models","github_url":"https://github.com/huggingface/speech-to-speech","owner":"huggingface","repo":"speech-to-speech","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":13280,"forks":1683,"topics":["ai","assistant","language-model","machine-learning","python","speech","speech-synthesis","speech-to-text","speech-translation"],"archived":false,"github_pushed_at":"2026-09-18T23:15:28+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-speech-to-speech","markdown_url":"https://www.graphcanon.com/tools/huggingface-speech-to-speech.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-speech-to-speech","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-speech-to-speech","shared_categories":["speech-audio"]},{"slug":"aigc-audio-audiogpt","name":"AudioGPT","tagline":"AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head","github_url":"https://github.com/AIGC-Audio/AudioGPT","owner":"AIGC-Audio","repo":"AudioGPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/128504843?v=4","primary_language":"Python","stars":10171,"forks":851,"topics":["audio","gpt","music","sound","speech","talking-head"],"archived":false,"github_pushed_at":"2024-07-06T21:35:18+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/aigc-audio-audiogpt","markdown_url":"https://www.graphcanon.com/tools/aigc-audio-audiogpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/aigc-audio-audiogpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=aigc-audio-audiogpt","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":10137,"forks":860,"topics":["python","realtime","speech-to-text"],"archived":false,"github_pushed_at":"2026-09-17T18:49:24+00:00","maintenance_label":"Active","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":"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":8381,"forks":1030,"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":"2026-09-19T15:48:12+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":"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":5696,"forks":1426,"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":"2026-09-19T21:31:02+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":"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":4031,"forks":405,"topics":["python","realtime","speech-synthesis","text-to-speech"],"archived":false,"github_pushed_at":"2026-09-19T23:35:24+00:00","maintenance_label":"Active","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":3340,"forks":584,"topics":["asr","automatic-speech-recognition","docker","openai-whisper","speech","speech-recognition","speech-to-text"],"archived":false,"github_pushed_at":"2026-08-09T20:36:38+00:00","maintenance_label":"Steady","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":"pannous-tensorflow-speech-recognition","name":"tensorflow-speech-recognition","tagline":"Speech recognition using TensorFlow deep learning framework","github_url":"https://github.com/pannous/tensorflow-speech-recognition","owner":"pannous","repo":"tensorflow-speech-recognition","owner_avatar_url":"https://avatars.githubusercontent.com/u/516118?v=4","primary_language":"Python","stars":2172,"forks":628,"topics":["deep-learning","neural-network","speech-recognition","speech-to-text","stt","tensorflow"],"archived":false,"github_pushed_at":"2024-01-17T14:27:13+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/pannous-tensorflow-speech-recognition","markdown_url":"https://www.graphcanon.com/tools/pannous-tensorflow-speech-recognition.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/pannous-tensorflow-speech-recognition","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=pannous-tensorflow-speech-recognition","shared_categories":["speech-audio"]},{"slug":"enemyx-net-vibevoice-comfyui","name":"VibeVoice-ComfyUI","tagline":"Comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech","github_url":"https://github.com/Enemyx-net/VibeVoice-ComfyUI","owner":"Enemyx-net","repo":"VibeVoice-ComfyUI","owner_avatar_url":"https://avatars.githubusercontent.com/u/228984999?v=4","primary_language":"Python","stars":1565,"forks":248,"topics":["ai-audio","ai-tts","ai-voice","ai-voice-clone","ai-voice-clonining","comfyui-custom-node","comfyui-custom-nodes-text-to-speech","comfyui-nodes","t2s","text-to-speech","tts","vibevoice","vibevoice-microsoft","voice-cloning","voice-generation","voice-generator"],"archived":false,"github_pushed_at":"2026-02-18T07:40:52+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/enemyx-net-vibevoice-comfyui","markdown_url":"https://www.graphcanon.com/tools/enemyx-net-vibevoice-comfyui.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/enemyx-net-vibevoice-comfyui","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=enemyx-net-vibevoice-comfyui","shared_categories":["speech-audio"]}]}}