{"data":{"node":{"slug":"openai-whisper","name":"whisper","tagline":"Robust Speech Recognition via Large-Scale Weak Supervision","github_url":"https://github.com/openai/whisper","owner":"openai","repo":"whisper","owner_avatar_url":"https://avatars.githubusercontent.com/u/14957082?v=4","primary_language":"Python","stars":106740,"forks":12971,"topics":[],"archived":false,"github_pushed_at":"2026-07-28T20:18:29+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/openai-whisper","markdown_url":"https://www.graphcanon.com/tools/openai-whisper.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openai-whisper","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openai-whisper"},"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":"openai","name":"openai"},{"slug":"speech-recognition","name":"speech-recognition"},{"slug":"weak-supervision","name":"weak supervision"}],"edges":[{"type":"alternative","direction":"out","explanation":"Both Whisper and LLaMA-Omni focus on seamless interaction with models for speech, but LLaMA-Omni integrates speech interaction capabilities into large language models while Whisper specifically handles robust speech recognition.","successor_context":null,"tool":{"slug":"ictnlp-llama-omni","name":"LLaMA-Omni","tagline":"End-to-end speech interaction model based on Llama-3.1-8B-Instruct","github_url":"https://github.com/ictnlp/LLaMA-Omni","owner":"ictnlp","repo":"LLaMA-Omni","owner_avatar_url":"https://avatars.githubusercontent.com/u/45630465?v=4","primary_language":"Python","stars":3146,"forks":224,"topics":["large-language-models","multimodal-large-language-models","speech-interaction","speech-language-model","speech-to-speech","speech-to-text"],"archived":false,"github_pushed_at":"2025-05-19T02:24:42+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/ictnlp-llama-omni","markdown_url":"https://www.graphcanon.com/tools/ictnlp-llama-omni.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ictnlp-llama-omni","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ictnlp-llama-omni"}},{"type":"related","direction":"out","explanation":null,"successor_context":null,"tool":{"slug":"ictnlp-llama-omni","name":"LLaMA-Omni","tagline":"End-to-end speech interaction model based on Llama-3.1-8B-Instruct","github_url":"https://github.com/ictnlp/LLaMA-Omni","owner":"ictnlp","repo":"LLaMA-Omni","owner_avatar_url":"https://avatars.githubusercontent.com/u/45630465?v=4","primary_language":"Python","stars":3146,"forks":224,"topics":["large-language-models","multimodal-large-language-models","speech-interaction","speech-language-model","speech-to-speech","speech-to-text"],"archived":false,"github_pushed_at":"2025-05-19T02:24:42+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/ictnlp-llama-omni","markdown_url":"https://www.graphcanon.com/tools/ictnlp-llama-omni.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ictnlp-llama-omni","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ictnlp-llama-omni"}},{"type":"related","direction":"out","explanation":"CosyVoice and Whisper are both models for voice generation but focus on different aspects: CosyVoice is more broadly multilingual and flexible.","successor_context":null,"tool":{"slug":"funaudiollm-cosyvoice","name":"CosyVoice","tagline":"Multi-lingual large voice generation model with full-stack abilities for inference, training and deployment.","github_url":"https://github.com/FunAudioLLM/CosyVoice","owner":"FunAudioLLM","repo":"CosyVoice","owner_avatar_url":"https://avatars.githubusercontent.com/u/167062371?v=4","primary_language":"Python","stars":22373,"forks":2584,"topics":["audio-generation","cantonese","chatbot","chatgpt","chinese","cosyvoice","cross-lingual","english","fine-grained","fine-tuning","gpt-4o","japanese","korean","multi-lingual","natural-language-generation","python","text-to-speech","tts","voice-cloning"],"archived":false,"github_pushed_at":"2026-05-25T18:15:40+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/funaudiollm-cosyvoice","markdown_url":"https://www.graphcanon.com/tools/funaudiollm-cosyvoice.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/funaudiollm-cosyvoice","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=funaudiollm-cosyvoice"}},{"type":"successor","direction":"out","explanation":"faster-whisper builds on Whisper to provide speed optimizations using CTranslate2.","successor_context":{"status":"recommended","reason":"Offers significant performance improvements."},"tool":{"slug":"systran-faster-whisper","name":"faster-whisper","tagline":"Faster Whisper transcription with CTranslate2","github_url":"https://github.com/SYSTRAN/faster-whisper","owner":"SYSTRAN","repo":"faster-whisper","owner_avatar_url":"https://avatars.githubusercontent.com/u/1520500?v=4","primary_language":"Python","stars":24689,"forks":2006,"topics":["deep-learning","inference","openai","quantization","speech-recognition","speech-to-text","transformer","whisper"],"archived":false,"github_pushed_at":"2025-11-19T14:40:46+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/systran-faster-whisper","markdown_url":"https://www.graphcanon.com/tools/systran-faster-whisper.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/systran-faster-whisper","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=systran-faster-whisper"}},{"type":"alternative","direction":"out","explanation":"whisper.cpp is a C/C++ port of the Whisper model, providing an alternative implementation for speech-to-text inference.","successor_context":null,"tool":{"slug":"ggml-org-whisper-cpp","name":"whisper.cpp","tagline":"Port of OpenAI's Whisper model in C/C++ for speech-to-text inference","github_url":"https://github.com/ggml-org/whisper.cpp","owner":"ggml-org","repo":"whisper.cpp","owner_avatar_url":"https://avatars.githubusercontent.com/u/134263123?v=4","primary_language":"C++","stars":52501,"forks":5971,"topics":["inference","openai","speech-recognition","speech-to-text","transformer","whisper"],"archived":false,"github_pushed_at":"2026-07-31T07:11:28+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/ggml-org-whisper-cpp","markdown_url":"https://www.graphcanon.com/tools/ggml-org-whisper-cpp.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ggml-org-whisper-cpp","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ggml-org-whisper-cpp"}},{"type":"successor","direction":"out","explanation":"whisperX extends Whisper with automatic speech recognition featuring word-level timestamps and diarization.","successor_context":{"status":"coexists","reason":"Provides enhanced functionality beyond basic transcription."},"tool":{"slug":"m-bain-whisperx","name":"whisperX","tagline":"WhisperX for automatic speech recognition with word-level timestamps and diarization","github_url":"https://github.com/m-bain/whisperX","owner":"m-bain","repo":"whisperX","owner_avatar_url":"https://avatars.githubusercontent.com/u/36994049?v=4","primary_language":"Python","stars":23329,"forks":2361,"topics":["asr","speech","speech-recognition","speech-to-text","whisper"],"archived":false,"github_pushed_at":"2026-07-13T08:30:07+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/m-bain-whisperx","markdown_url":"https://www.graphcanon.com/tools/m-bain-whisperx.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/m-bain-whisperx","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=m-bain-whisperx"}},{"type":"alternative","direction":"out","explanation":"Whisper and ChatTTS both deal with speech generation, though Whisper focuses on robust speech recognition while ChatTTS is a generative speech model.","successor_context":null,"tool":{"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","stars_delta_30d":140,"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"}},{"type":"depends_on","direction":"out","explanation":"Whisper uses PyTorch for training and testing, which is a core part of NVIDIA's DeepLearningExamples repository that provides scripts for easy deployment on NVIDIA GPUs.","successor_context":null,"tool":{"slug":"nvidia-deeplearningexamples","name":"DeepLearningExamples","tagline":"State-of-the-Art Deep Learning scripts for various applications","github_url":"https://github.com/NVIDIA/DeepLearningExamples","owner":"NVIDIA","repo":"DeepLearningExamples","owner_avatar_url":"https://avatars.githubusercontent.com/u/1728152?v=4","primary_language":"Jupyter Notebook","stars":14844,"forks":3408,"topics":["computer-vision","deep-learning","drug-discovery","forecasting","large-language-models","mxnet","nlp","paddlepaddle","pytorch","recommender-systems","speech-recognition","speech-synthesis","tensorflow","tensorflow2","translation"],"archived":false,"github_pushed_at":"2024-08-12T14:01:29+00:00","maintenance_label":"Dormant","stars_delta_30d":14,"url":"https://www.graphcanon.com/tools/nvidia-deeplearningexamples","markdown_url":"https://www.graphcanon.com/tools/nvidia-deeplearningexamples.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nvidia-deeplearningexamples","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nvidia-deeplearningexamples"}},{"type":"related","direction":"in","explanation":"Both LLaMA-Omni and Whisper deal with speech processing, but they serve different purposes. Whisper focuses on robust speech recognition, while LLaMA-Omni is about generating both text and speech responses from speech inputs.","successor_context":null,"tool":{"slug":"ictnlp-llama-omni","name":"LLaMA-Omni","tagline":"End-to-end speech interaction model based on Llama-3.1-8B-Instruct","github_url":"https://github.com/ictnlp/LLaMA-Omni","owner":"ictnlp","repo":"LLaMA-Omni","owner_avatar_url":"https://avatars.githubusercontent.com/u/45630465?v=4","primary_language":"Python","stars":3146,"forks":224,"topics":["large-language-models","multimodal-large-language-models","speech-interaction","speech-language-model","speech-to-speech","speech-to-text"],"archived":false,"github_pushed_at":"2025-05-19T02:24:42+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/ictnlp-llama-omni","markdown_url":"https://www.graphcanon.com/tools/ictnlp-llama-omni.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ictnlp-llama-omni","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ictnlp-llama-omni"}},{"type":"depends_on","direction":"in","explanation":"The course overview mentions functionality to understand voice and send voice notes, tasks which can be facilitated by Whisper’s speech recognition capabilities. This indicates that the repository likely relies on or could benefit from integrating Whisper.","successor_context":null,"tool":{"slug":"neural-maze-ava-whatsapp-agent-course","name":"ava-whatsapp-agent-course","tagline":"Meet Ava, the WhatsApp Agent","github_url":"https://github.com/neural-maze/ava-whatsapp-agent-course","owner":"neural-maze","repo":"ava-whatsapp-agent-course","owner_avatar_url":"https://avatars.githubusercontent.com/u/151655127?v=4","primary_language":"Python","stars":1672,"forks":419,"topics":["agent","agent-based","agentic-workflow","agents","stt","tts","vector-database"],"archived":false,"github_pushed_at":"2025-10-20T19:12:20+00:00","maintenance_label":"Slowing","stars_delta_30d":8,"url":"https://www.graphcanon.com/tools/neural-maze-ava-whatsapp-agent-course","markdown_url":"https://www.graphcanon.com/tools/neural-maze-ava-whatsapp-agent-course.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/neural-maze-ava-whatsapp-agent-course","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=neural-maze-ava-whatsapp-agent-course"}},{"type":"integrates_with","direction":"in","explanation":"Whisper leverages 🤗 Transformers for its speech recognition capabilities, likely using pre-trained models from this framework for speech-to-text conversion.","successor_context":null,"tool":{"slug":"huggingface-transformers","name":"transformers","tagline":"Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models","github_url":"https://github.com/huggingface/transformers","owner":"huggingface","repo":"transformers","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":164121,"forks":34249,"topics":["audio","deep-learning","deepseek","gemma","glm","hacktoberfest","llm","machine-learning","model-hub","natural-language-processing","nlp","pretrained-models","python","pytorch","pytorch-transformers","qwen","speech-recognition","transformer","vlm"],"archived":false,"github_pushed_at":"2026-08-15T22:28:12+00:00","maintenance_label":"Very active","stars_delta_30d":1457,"url":"https://www.graphcanon.com/tools/huggingface-transformers","markdown_url":"https://www.graphcanon.com/tools/huggingface-transformers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-transformers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-transformers"}}],"neighbours":[{"slug":"huggingface-transformers","name":"transformers","tagline":"Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models","github_url":"https://github.com/huggingface/transformers","owner":"huggingface","repo":"transformers","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":164121,"forks":34249,"topics":["audio","deep-learning","deepseek","gemma","glm","hacktoberfest","llm","machine-learning","model-hub","natural-language-processing","nlp","pretrained-models","python","pytorch","pytorch-transformers","qwen","speech-recognition","transformer","vlm"],"archived":false,"github_pushed_at":"2026-08-15T22:28:12+00:00","maintenance_label":"Very active","stars_delta_30d":1457,"url":"https://www.graphcanon.com/tools/huggingface-transformers","markdown_url":"https://www.graphcanon.com/tools/huggingface-transformers.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-transformers","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-transformers","shared_categories":["speech-audio"]},{"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":"Very active","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":"ggml-org-whisper-cpp","name":"whisper.cpp","tagline":"Port of OpenAI's Whisper model in C/C++ for speech-to-text inference","github_url":"https://github.com/ggml-org/whisper.cpp","owner":"ggml-org","repo":"whisper.cpp","owner_avatar_url":"https://avatars.githubusercontent.com/u/134263123?v=4","primary_language":"C++","stars":52501,"forks":5971,"topics":["inference","openai","speech-recognition","speech-to-text","transformer","whisper"],"archived":false,"github_pushed_at":"2026-07-31T07:11:28+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/ggml-org-whisper-cpp","markdown_url":"https://www.graphcanon.com/tools/ggml-org-whisper-cpp.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ggml-org-whisper-cpp","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ggml-org-whisper-cpp","shared_categories":["speech-audio"]},{"slug":"mudler-localai","name":"LocalAI","tagline":"Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.","github_url":"https://github.com/mudler/LocalAI","owner":"mudler","repo":"LocalAI","owner_avatar_url":"https://avatars.githubusercontent.com/u/2420543?v=4","primary_language":"Go","stars":48500,"forks":4362,"topics":["agents","ai","api","audio-generation","decentralized","distributed","image-generation","libp2p","llama","llm","mamba","mcp","musicgen","object-detection","rerank","stable-diffusion","text-generation","tts"],"archived":false,"github_pushed_at":"2026-08-16T05:07:25+00:00","maintenance_label":"Very active","stars_delta_30d":924,"url":"https://www.graphcanon.com/tools/mudler-localai","markdown_url":"https://www.graphcanon.com/tools/mudler-localai.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mudler-localai","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mudler-localai","shared_categories":["speech-audio"]},{"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":45832,"forks":6158,"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":"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","stars_delta_30d":140,"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":"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":39218,"forks":4669,"topics":[],"archived":false,"github_pushed_at":"2024-08-19T07:45:36+00:00","maintenance_label":"Dormant","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","shared_categories":["speech-audio"]},{"slug":"myshell-ai-openvoice","name":"OpenVoice","tagline":"Instant voice cloning using an audio foundation model","github_url":"https://github.com/myshell-ai/OpenVoice","owner":"myshell-ai","repo":"OpenVoice","owner_avatar_url":"https://avatars.githubusercontent.com/u/127754094?v=4","primary_language":"Python","stars":37044,"forks":4146,"topics":["text-to-speech","tts","voice-clone","zero-shot-tts"],"archived":false,"github_pushed_at":"2025-04-19T16:00:00+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/myshell-ai-openvoice","markdown_url":"https://www.graphcanon.com/tools/myshell-ai-openvoice.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/myshell-ai-openvoice","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=myshell-ai-openvoice","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":36913,"forks":5197,"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":"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":"Active","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":"zackriya-solutions-meetily","name":"meetily","tagline":"Privacy first, AI meeting assistant with local processing","github_url":"https://github.com/Zackriya-Solutions/meetily","owner":"Zackriya-Solutions","repo":"meetily","owner_avatar_url":"https://avatars.githubusercontent.com/u/82556810?v=4","primary_language":"Rust","stars":29268,"forks":3115,"topics":["ai","ai-meeting-assistant","llm","local-ai","mac","meeting-minutes","meeting-notes","offline-first","ollama","parakeet","privacy-focused","privacy-tools","rust","self-hosted","sortformer","speech-to-text","transcription","whisper","whisper-cpp","windows"],"archived":false,"github_pushed_at":"2026-06-05T13:53:17+00:00","maintenance_label":"Steady","stars_delta_30d":4047,"url":"https://www.graphcanon.com/tools/zackriya-solutions-meetily","markdown_url":"https://www.graphcanon.com/tools/zackriya-solutions-meetily.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zackriya-solutions-meetily","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zackriya-solutions-meetily","shared_categories":["speech-audio"]},{"slug":"cjpais-handy","name":"Handy","tagline":"Free, open source speech-to-text application for offline use","github_url":"https://github.com/cjpais/Handy","owner":"cjpais","repo":"Handy","owner_avatar_url":"https://avatars.githubusercontent.com/u/1559480?v=4","primary_language":"Rust","stars":27869,"forks":2426,"topics":["accessibility","cross-platform","speech-to-text","tauri-v2"],"archived":false,"github_pushed_at":"2026-07-28T10:51:53+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/cjpais-handy","markdown_url":"https://www.graphcanon.com/tools/cjpais-handy.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/cjpais-handy","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=cjpais-handy","shared_categories":["speech-audio"]}]}}