{"data":{"node":{"slug":"k2-fsa-sherpa-onnx","name":"sherpa-onnx","tagline":"Speech-to-text and related audio processing tools using ONNX with cross-platform support","github_url":"https://github.com/k2-fsa/sherpa-onnx","owner":"k2-fsa","repo":"sherpa-onnx","owner_avatar_url":"https://avatars.githubusercontent.com/u/71431748?v=4","primary_language":"C++","stars":13842,"forks":1596,"topics":["aarch64","android","arm32","asr","cpp","csharp","dotnet","ios","lazarus","linux","macos","mfc","object-pascal","onnx","raspberry-pi","risc-v","speech-to-text","text-to-speech","vits","windows"],"archived":false,"github_pushed_at":"2026-07-29T03:35:02+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/k2-fsa-sherpa-onnx","markdown_url":"https://www.graphcanon.com/tools/k2-fsa-sherpa-onnx.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/k2-fsa-sherpa-onnx","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=k2-fsa-sherpa-onnx"},"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":"aarch64","name":"aarch64"},{"slug":"android","name":"android"},{"slug":"arm32","name":"arm32"},{"slug":"asr","name":"asr"},{"slug":"cpp","name":"cpp"},{"slug":"csharp","name":"csharp"},{"slug":"dotnet","name":"dotnet"},{"slug":"ios","name":"ios"}],"edges":[],"neighbours":[{"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","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":"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":"supertone-inc-supertonic","name":"supertonic","tagline":"Lightning-Fast On-Device Multilingual TTS via ONNX","github_url":"https://github.com/supertone-inc/supertonic","owner":"supertone-inc","repo":"supertonic","owner_avatar_url":"https://avatars.githubusercontent.com/u/61007505?v=4","primary_language":"Swift","stars":13543,"forks":1427,"topics":["cpp","csharp","flutter","go","ios","java","lightweight","multilingual","nodejs","on-device","onnx","onnxruntime","python","rust","speech-synthesis","swift","text-to-speech","tts","web","webgpu"],"archived":false,"github_pushed_at":"2026-07-24T04:00:17+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/supertone-inc-supertonic","markdown_url":"https://www.graphcanon.com/tools/supertone-inc-supertonic.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/supertone-inc-supertonic","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=supertone-inc-supertonic","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":"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":"uberi-speech-recognition","name":"speech_recognition","tagline":"Speech recognition module for Python","github_url":"https://github.com/Uberi/speech_recognition","owner":"Uberi","repo":"speech_recognition","owner_avatar_url":"https://avatars.githubusercontent.com/u/437196?v=4","primary_language":"Python","stars":8977,"forks":2415,"topics":["audio","python","speech-recognition","speech-to-text"],"archived":false,"github_pushed_at":"2026-06-16T22:33:12+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/uberi-speech-recognition","markdown_url":"https://www.graphcanon.com/tools/uberi-speech-recognition.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/uberi-speech-recognition","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=uberi-speech-recognition","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":"mahmoudashraf97-whisper-diarization","name":"whisper-diarization","tagline":"Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper","github_url":"https://github.com/MahmoudAshraf97/whisper-diarization","owner":"MahmoudAshraf97","repo":"whisper-diarization","owner_avatar_url":"https://avatars.githubusercontent.com/u/32404268?v=4","primary_language":"Jupyter Notebook","stars":5615,"forks":503,"topics":["asr","speaker-diarization","speech","speech-recognition","speech-to-text","whisper"],"archived":false,"github_pushed_at":"2026-02-23T15:56:59+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/mahmoudashraf97-whisper-diarization","markdown_url":"https://www.graphcanon.com/tools/mahmoudashraf97-whisper-diarization.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mahmoudashraf97-whisper-diarization","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mahmoudashraf97-whisper-diarization","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":5265,"forks":858,"topics":["fastapi","huggingface-spaces","kokoro","kokoro-tts","openai-compatible-api","openwebui","pytorch","sillytavern","text-to-speech","tts","tts-api","uv"],"archived":false,"github_pushed_at":"2026-07-21T03:16:48+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":"sanchit-gandhi-whisper-jax","name":"whisper-jax","tagline":"JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.","github_url":"https://github.com/sanchit-gandhi/whisper-jax","owner":"sanchit-gandhi","repo":"whisper-jax","owner_avatar_url":"https://avatars.githubusercontent.com/u/93869735?v=4","primary_language":"Jupyter Notebook","stars":4684,"forks":411,"topics":["deep-learning","jax","speech-recognition","speech-to-text","whisper"],"archived":false,"github_pushed_at":"2024-04-03T12:12:52+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/sanchit-gandhi-whisper-jax","markdown_url":"https://www.graphcanon.com/tools/sanchit-gandhi-whisper-jax.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/sanchit-gandhi-whisper-jax","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=sanchit-gandhi-whisper-jax","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"]}]}}