{"data":{"node":{"slug":"autoark-gpa","name":"GPA","tagline":"General Purpose Audio for ASR, TTS, and Voice Conversion","github_url":"https://github.com/AutoArk/GPA","owner":"AutoArk","repo":"GPA","owner_avatar_url":"https://avatars.githubusercontent.com/u/224494850?v=4","primary_language":"Python","stars":1780,"forks":123,"topics":["asr","automatic-speech-recognition","text-to-speech","transformer","tts","vc","voice-conversion"],"archived":false,"github_pushed_at":"2026-05-25T08:02:41+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/autoark-gpa","markdown_url":"https://www.graphcanon.com/tools/autoark-gpa.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/autoark-gpa","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=autoark-gpa"},"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":"asr","name":"asr"},{"slug":"automatic-speech-recognition","name":"automatic-speech-recognition"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"transformer","name":"transformer"},{"slug":"tts","name":"tts"},{"slug":"vc","name":"vc"},{"slug":"voice-conversion","name":"voice-conversion"}],"edges":[],"neighbours":[{"slug":"rvc-boss-gpt-sovits","name":"GPT-SoVITS","tagline":"Voice Cloning and Text-to-Speech with Minimal Voice Data","github_url":"https://github.com/RVC-Boss/GPT-SoVITS","owner":"RVC-Boss","repo":"GPT-SoVITS","owner_avatar_url":"https://avatars.githubusercontent.com/u/129054828?v=4","primary_language":"Python","stars":60178,"forks":6553,"topics":["text-to-speech","tts","vits","voice-clone","voice-cloneai","voice-cloning"],"archived":false,"github_pushed_at":"2026-07-22T08:21:07+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/rvc-boss-gpt-sovits","markdown_url":"https://www.graphcanon.com/tools/rvc-boss-gpt-sovits.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rvc-boss-gpt-sovits","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rvc-boss-gpt-sovits","shared_categories":["speech-audio"]},{"slug":"openbmb-voxcpm","name":"VoxCPM","tagline":"Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning","github_url":"https://github.com/OpenBMB/VoxCPM","owner":"OpenBMB","repo":"VoxCPM","owner_avatar_url":"https://avatars.githubusercontent.com/u/89920203?v=4","primary_language":"Python","stars":34452,"forks":3939,"topics":["audio","deeplearning","minicpm","multilingual","python","pytorch","speech","speech-synthesis","text-to-speech","tts","tts-model","voice-cloning","voice-design","voxcpm"],"archived":false,"github_pushed_at":"2026-07-08T09:46:11+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/openbmb-voxcpm","markdown_url":"https://www.graphcanon.com/tools/openbmb-voxcpm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openbmb-voxcpm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openbmb-voxcpm","shared_categories":["speech-audio"]},{"slug":"speechbrain-speechbrain","name":"speechbrain","tagline":"A PyTorch-based Speech Toolkit","github_url":"https://github.com/speechbrain/speechbrain","owner":"speechbrain","repo":"speechbrain","owner_avatar_url":"https://avatars.githubusercontent.com/u/54749030?v=4","primary_language":"Python","stars":11725,"forks":1712,"topics":["asr","audio","audio-processing","deep-learning","huggingface","language-model","pytorch","speaker-diarization","speaker-recognition","speaker-verification","speech-enhancement","speech-processing","speech-recognition","speech-separation","speech-to-text","speech-toolkit","speechrecognition","spoken-language-understanding","transformers","voice-recognition"],"archived":false,"github_pushed_at":"2026-06-15T11:24:25+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/speechbrain-speechbrain","markdown_url":"https://www.graphcanon.com/tools/speechbrain-speechbrain.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/speechbrain-speechbrain","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=speechbrain-speechbrain","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":"espnet-espnet","name":"espnet","tagline":"End-to-End Speech Processing Toolkit","github_url":"https://github.com/espnet/espnet","owner":"espnet","repo":"espnet","owner_avatar_url":"https://avatars.githubusercontent.com/u/34493687?v=4","primary_language":"Python","stars":9903,"forks":2421,"topics":["chainer","deep-learning","end-to-end","kaldi","machine-translation","pytorch","singing-voice-synthesis","speaker-diarization","speech-enhancement","speech-recognition","speech-separation","speech-synthesis","speech-translation","spoken-language-understanding","text-to-speech","voice-conversion"],"archived":false,"github_pushed_at":"2026-07-28T14:36:55+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/espnet-espnet","markdown_url":"https://www.graphcanon.com/tools/espnet-espnet.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/espnet-espnet","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=espnet-espnet","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":"jaywalnut310-vits","name":"vits","tagline":"VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","github_url":"https://github.com/jaywalnut310/vits","owner":"jaywalnut310","repo":"vits","owner_avatar_url":"https://avatars.githubusercontent.com/u/20279210?v=4","primary_language":"Python","stars":7889,"forks":1384,"topics":["deep-learning","pytorch","speech-synthesis","text-to-speech","tts"],"archived":false,"github_pushed_at":"2023-12-06T01:29:50+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/jaywalnut310-vits","markdown_url":"https://www.graphcanon.com/tools/jaywalnut310-vits.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jaywalnut310-vits","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jaywalnut310-vits","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":"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":4203,"forks":693,"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":"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":"jik876-hifi-gan","name":"hifi-gan","tagline":"Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","github_url":"https://github.com/jik876/hifi-gan","owner":"jik876","repo":"hifi-gan","owner_avatar_url":"https://avatars.githubusercontent.com/u/65878508?v=4","primary_language":"Python","stars":2363,"forks":555,"topics":["deep-learning","gan","hifi-gan","pytorch","speech-synthesis","text-to-speech","tts","vocoder"],"archived":false,"github_pushed_at":"2024-07-27T20:56:30+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/jik876-hifi-gan","markdown_url":"https://www.graphcanon.com/tools/jik876-hifi-gan.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jik876-hifi-gan","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jik876-hifi-gan","shared_categories":["speech-audio"]},{"slug":"kyubyong-dc-tts","name":"dc_tts","tagline":"A TensorFlow Implementation of DC-TTS","github_url":"https://github.com/Kyubyong/dc_tts","owner":"Kyubyong","repo":"dc_tts","owner_avatar_url":"https://avatars.githubusercontent.com/u/13579986?v=4","primary_language":"Python","stars":1156,"forks":360,"topics":["speech","speech-to-text","tts"],"archived":false,"github_pushed_at":"2023-04-14T14:54:06+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/kyubyong-dc-tts","markdown_url":"https://www.graphcanon.com/tools/kyubyong-dc-tts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/kyubyong-dc-tts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=kyubyong-dc-tts","shared_categories":["speech-audio"]}]}}