{"data":{"node":{"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":"Very 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"},"categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"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":"conversational-ai","name":"conversational-ai"},{"slug":"local-llm","name":"local-llm"},{"slug":"self-hosted","name":"self-hosted"},{"slug":"speech-to-text","name":"speech-to-text"},{"slug":"telephony","name":"telephony"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"visual-workflow-builder","name":"visual-workflow-builder"}],"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":"emcie-co-parlant","name":"parlant","tagline":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","github_url":"https://github.com/emcie-co/parlant","owner":"emcie-co","repo":"parlant","owner_avatar_url":"https://avatars.githubusercontent.com/u/160175171?v=4","primary_language":"Python","stars":18253,"forks":1551,"topics":["ai-agents","ai-alignment","customer-service","customer-success","gemini","genai","hacktoberfest","llama3","llm","openai","python"],"archived":false,"github_pushed_at":"2026-07-12T19:40:55+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/emcie-co-parlant","markdown_url":"https://www.graphcanon.com/tools/emcie-co-parlant.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/emcie-co-parlant","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=emcie-co-parlant","shared_categories":[]},{"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":"abus-aikorea-voice-pro","name":"voice-pro","tagline":"Gradio WebUI for TTS and voice cloning with audio processing capabilities","github_url":"https://github.com/abus-aikorea/voice-pro","owner":"abus-aikorea","repo":"voice-pro","owner_avatar_url":"https://avatars.githubusercontent.com/u/161691694?v=4","primary_language":"Python","stars":11348,"forks":1663,"topics":["audiobook","faster-whisper","gradio","karaoke","podcasts","speech-recognition","speech-synthesis","speech-to-text","subtitles","text-to-speech","transcription","translator","tts","voice-cloning","voice-conversion","webui","whisper","whisperx","yt-dlp"],"archived":false,"github_pushed_at":"2026-07-13T01:28:10+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/abus-aikorea-voice-pro","markdown_url":"https://www.graphcanon.com/tools/abus-aikorea-voice-pro.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/abus-aikorea-voice-pro","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=abus-aikorea-voice-pro","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":"debpalash-omnivoice-studio","name":"OmniVoice-Studio","tagline":"The open-source ElevenLabs alternative for local voice cloning and related tasks","github_url":"https://github.com/debpalash/OmniVoice-Studio","owner":"debpalash","repo":"OmniVoice-Studio","owner_avatar_url":"https://avatars.githubusercontent.com/u/4178343?v=4","primary_language":"Python","stars":9209,"forks":1494,"topics":["asr","audiobook","dubbing","dubbing-ai","elevenlabs","local-ai","omnivoice","omnivoice-studio","self-hosted","speech-recognition","speech-to-text","text-to-speech","transcription","tts","video-editing","voice-ai","voice-cloning","voice-generation"],"archived":false,"github_pushed_at":"2026-07-28T19:51:31+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/debpalash-omnivoice-studio","markdown_url":"https://www.graphcanon.com/tools/debpalash-omnivoice-studio.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/debpalash-omnivoice-studio","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=debpalash-omnivoice-studio","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":8219,"forks":1025,"topics":["ai","assistant","language-model","machine-learning","python","speech","speech-synthesis","speech-to-text","speech-translation"],"archived":false,"github_pushed_at":"2026-07-30T11:35:50+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":"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"]},{"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"]},{"slug":"alexpinel-dot","name":"Dot","tagline":"Text-To-Speech, RAG, and LLMs. All local!","github_url":"https://github.com/alexpinel/Dot","owner":"alexpinel","repo":"Dot","owner_avatar_url":"https://avatars.githubusercontent.com/u/93524949?v=4","primary_language":"JavaScript","stars":1911,"forks":110,"topics":["document-chat","embeddings","faiss","langchain","llamacpp","llm","local","phi-3","privategpt","rag","self-hosted","standalone","standalone-app","tts","whisper-cpp"],"archived":false,"github_pushed_at":"2024-12-09T15:46:44+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/alexpinel-dot","markdown_url":"https://www.graphcanon.com/tools/alexpinel-dot.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alexpinel-dot","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alexpinel-dot","shared_categories":["speech-audio"]}]}}