{"data":{"node":{"slug":"nari-labs-dia2","name":"dia2","tagline":"TTS model capable of streaming conversational audio in real-time.","github_url":"https://github.com/nari-labs/dia2","owner":"nari-labs","repo":"dia2","owner_avatar_url":"https://avatars.githubusercontent.com/u/208232306?v=4","primary_language":"Python","stars":1160,"forks":99,"topics":["open-weight","text-to-speech"],"archived":false,"github_pushed_at":"2025-11-29T00:51:56+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/nari-labs-dia2","markdown_url":"https://www.graphcanon.com/tools/nari-labs-dia2.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nari-labs-dia2","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nari-labs-dia2"},"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":"open-weight","name":"open-weight"},{"slug":"text-to-speech","name":"text-to-speech"}],"edges":[],"neighbours":[{"slug":"2noise-chattts","name":"ChatTTS","tagline":"A generative speech model for daily dialogue","github_url":"https://github.com/2noise/ChatTTS","owner":"2noise","repo":"ChatTTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/164844019?v=4","primary_language":"Python","stars":39768,"forks":4257,"topics":["agent","chat","chatgpt","chattts","chinese","chinese-language","english","english-language","gpt","llm","llm-agent","natural-language-inference","python","text-to-speech","torch","torchaudio","tts"],"archived":false,"github_pushed_at":"2026-04-10T16:33:48+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/2noise-chattts","markdown_url":"https://www.graphcanon.com/tools/2noise-chattts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/2noise-chattts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=2noise-chattts","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":"nari-labs-dia","name":"dia","tagline":"A TTS model for generating ultra-realistic dialogue","github_url":"https://github.com/nari-labs/dia","owner":"nari-labs","repo":"dia","owner_avatar_url":"https://avatars.githubusercontent.com/u/208232306?v=4","primary_language":"Python","stars":19361,"forks":1688,"topics":["ai","open-weight","text-to-speech"],"archived":false,"github_pushed_at":"2025-11-19T21:11:55+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/nari-labs-dia","markdown_url":"https://www.graphcanon.com/tools/nari-labs-dia.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nari-labs-dia","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nari-labs-dia","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":"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":10172,"forks":850,"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":"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":"snakers4-silero-models","name":"silero-models","tagline":"Silero Models provide simple access to pre-trained text-to-speech models","github_url":"https://github.com/snakers4/silero-models","owner":"snakers4","repo":"silero-models","owner_avatar_url":"https://avatars.githubusercontent.com/u/12515440?v=4","primary_language":"Jupyter Notebook","stars":6030,"forks":369,"topics":["armenian","azerbaijani","belarus","colab","georgian","kazakh","kyrgyz","pretrained-models","pytorch","russian","speech","speech-synthesis","speech-to-text","tajik","text-to-speech","torch-hub","tts","tts-models","ukrainian","uzbek"],"archived":false,"github_pushed_at":"2026-06-04T05:33:28+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/snakers4-silero-models","markdown_url":"https://www.graphcanon.com/tools/snakers4-silero-models.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/snakers4-silero-models","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=snakers4-silero-models","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":"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":"rsxdalv-tts-webui","name":"TTS-WebUI","tagline":"A comprehensive WebUI for multiple TTS systems","github_url":"https://github.com/rsxdalv/TTS-WebUI","owner":"rsxdalv","repo":"TTS-WebUI","owner_avatar_url":"https://avatars.githubusercontent.com/u/6757283?v=4","primary_language":"TypeScript","stars":3216,"forks":326,"topics":["ace-step","ai","audio-generation","cosyvoice","generative-ai","generator","gradio","music","musicgen","openai-api","openvoice","rvc","styletts2","text-to-speech","tortoise-tts","tts","vocos"],"archived":false,"github_pushed_at":"2026-07-27T13:23:40+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/rsxdalv-tts-webui","markdown_url":"https://www.graphcanon.com/tools/rsxdalv-tts-webui.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rsxdalv-tts-webui","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rsxdalv-tts-webui","shared_categories":["speech-audio"]}]}}