{"data":{"node":{"slug":"suno-ai-bark","name":"bark","tagline":"Text-Prompted Generative Audio Model","github_url":"https://github.com/suno-ai/bark","owner":"suno-ai","repo":"bark","owner_avatar_url":"https://avatars.githubusercontent.com/u/99442120?v=4","primary_language":"Jupyter Notebook","stars":39272,"forks":4669,"topics":[],"archived":false,"github_pushed_at":"2024-08-19T07:45:36+00:00","maintenance_label":"Dormant","stars_delta_30d":54,"url":"https://www.graphcanon.com/tools/suno-ai-bark","markdown_url":"https://www.graphcanon.com/tools/suno-ai-bark.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/suno-ai-bark","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=suno-ai-bark"},"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":"audio-generation","name":"audio-generation"},{"slug":"cpu","name":"cpu"},{"slug":"generative-model","name":"generative-model"},{"slug":"gpu","name":"gpu"},{"slug":"hardware-requirements","name":"hardware requirements"},{"slug":"inference-speed","name":"inference speed"},{"slug":"pytorch","name":"pytorch"},{"slug":"text-to-speech","name":"text-to-speech"}],"edges":[],"neighbours":[{"slug":"coqui-ai-tts","name":"TTS","tagline":"🐸💬 - a deep learning toolkit for Text-to-Speech","github_url":"https://github.com/coqui-ai/TTS","owner":"coqui-ai","repo":"TTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/75583352?v=4","primary_language":"Python","stars":46029,"forks":6157,"topics":["deep-learning","glow-tts","hifigan","melgan","multi-speaker-tts","python","pytorch","speaker-encoder","speaker-encodings","speech","speech-synthesis","tacotron","text-to-speech","tts","tts-model","vocoder","voice-cloning","voice-conversion","voice-synthesis"],"archived":false,"github_pushed_at":"2024-08-16T12:07:14+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/coqui-ai-tts","markdown_url":"https://www.graphcanon.com/tools/coqui-ai-tts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/coqui-ai-tts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=coqui-ai-tts","shared_categories":["speech-audio"]},{"slug":"babysor-mockingbird","name":"MockingBird","tagline":"Clone a voice in 5 seconds to generate arbitrary speech in real-time","github_url":"https://github.com/babysor/MockingBird","owner":"babysor","repo":"MockingBird","owner_avatar_url":"https://avatars.githubusercontent.com/u/7423248?v=4","primary_language":"Python","stars":36906,"forks":5178,"topics":["ai","deep-learning","pytorch","speech","text-to-speech","tts"],"archived":false,"github_pushed_at":"2026-03-03T14:59:58+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/babysor-mockingbird","markdown_url":"https://www.graphcanon.com/tools/babysor-mockingbird.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/babysor-mockingbird","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=babysor-mockingbird","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":19400,"forks":1690,"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":"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":"netease-youdao-emotivoice","name":"EmotiVoice","tagline":"A Multi-Voice and Prompt-Controlled TTS Engine","github_url":"https://github.com/netease-youdao/EmotiVoice","owner":"netease-youdao","repo":"EmotiVoice","owner_avatar_url":"https://avatars.githubusercontent.com/u/3909232?v=4","primary_language":"Python","stars":8528,"forks":756,"topics":["ai","deep-learning","emotion","emotivoice","multi-speaker","prompt","python","pytorch","speech","speech-synthesis","style","text-to-speech","tts"],"archived":false,"github_pushed_at":"2026-09-03T08:30:35+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/netease-youdao-emotivoice","markdown_url":"https://www.graphcanon.com/tools/netease-youdao-emotivoice.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/netease-youdao-emotivoice","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=netease-youdao-emotivoice","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":6115,"forks":373,"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":"2026-07-31T16:28:45+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":"remsky-kokoro-fastapi","name":"Kokoro-FastAPI","tagline":"Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model","github_url":"https://github.com/remsky/Kokoro-FastAPI","owner":"remsky","repo":"Kokoro-FastAPI","owner_avatar_url":"https://avatars.githubusercontent.com/u/25017870?v=4","primary_language":"Python","stars":5461,"forks":902,"topics":["fastapi","kokoro","kokoro-82m","kokoro-tts","multi-speaker-tts","mutilingual-audio","openai-compatible-api","openwebui","pytorch","read-along","sillytavern","ssml","text-to-speech","tts","tts-api","tts-captions","tts-generation","voice-clone-tool"],"archived":false,"github_pushed_at":"2026-09-10T05:45:23+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/remsky-kokoro-fastapi","markdown_url":"https://www.graphcanon.com/tools/remsky-kokoro-fastapi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/remsky-kokoro-fastapi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=remsky-kokoro-fastapi","shared_categories":["speech-audio"]},{"slug":"metavoiceio-metavoice-src","name":"metavoice-src","tagline":"Foundational model for human-like, expressive TTS","github_url":"https://github.com/metavoiceio/metavoice-src","owner":"metavoiceio","repo":"metavoice-src","owner_avatar_url":"https://avatars.githubusercontent.com/u/107063843?v=4","primary_language":"Python","stars":4207,"forks":689,"topics":["ai","deep-learning","pytorch","speech","speech-synthesis","text-to-speech","tts","voice-clone","zero-shot-tts"],"archived":false,"github_pushed_at":"2024-07-30T22:13:01+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/metavoiceio-metavoice-src","markdown_url":"https://www.graphcanon.com/tools/metavoiceio-metavoice-src.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/metavoiceio-metavoice-src","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=metavoiceio-metavoice-src","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":3266,"forks":333,"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":"2026-09-07T08:54:58+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"]},{"slug":"camb-ai-mars5-tts","name":"MARS5-TTS","tagline":"MARS5 speech model TTS from CAMB.AI","github_url":"https://github.com/Camb-ai/MARS5-TTS","owner":"Camb-ai","repo":"MARS5-TTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/106663884?v=4","primary_language":"Jupyter Notebook","stars":2819,"forks":246,"topics":["prosody","speech","speech-synthesis","text-to-speech","voice-cloneai","voice-cloning"],"archived":false,"github_pushed_at":"2024-08-01T10:42:51+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/camb-ai-mars5-tts","markdown_url":"https://www.graphcanon.com/tools/camb-ai-mars5-tts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/camb-ai-mars5-tts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=camb-ai-mars5-tts","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":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":"Active","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":"lifeiteng-vall-e","name":"vall-e","tagline":"PyTorch implementation of VALL-E for Zero-Shot Text-To-Speech","github_url":"https://github.com/lifeiteng/vall-e","owner":"lifeiteng","repo":"vall-e","owner_avatar_url":"https://avatars.githubusercontent.com/u/3107839?v=4","primary_language":"Python","stars":2218,"forks":327,"topics":["chatgpt","in-context-learning","large-language-models","text-to-speech","tts","vall-e","valle"],"archived":false,"github_pushed_at":"2025-09-10T16:08:02+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/lifeiteng-vall-e","markdown_url":"https://www.graphcanon.com/tools/lifeiteng-vall-e.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/lifeiteng-vall-e","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=lifeiteng-vall-e","shared_categories":["speech-audio"]}]}}