{"data":{"slug":"fatchord-wavernn","name":"WaveRNN","tagline":"WaveRNN Vocoder + TTS","github_url":"https://github.com/fatchord/WaveRNN","owner":"fatchord","repo":"WaveRNN","owner_avatar_url":"https://avatars.githubusercontent.com/u/37295764?v=4","primary_language":"Python","stars":2190,"forks":687,"topics":["neural-vocoder","pytorch","speech-synthesis","tacotron","text-to-speech","tts","wavernn"],"archived":false,"github_pushed_at":"2022-07-02T14:21:35+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/fatchord-wavernn","markdown_url":"https://www.graphcanon.com/tools/fatchord-wavernn.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fatchord-wavernn","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fatchord-wavernn","description":"WaveRNN Vocoder + TTS","homepage_url":"https://fatchord.github.io/model_outputs/","license":"MIT","open_issues":108,"watchers":85,"ai_summary":"Repository for WaveRNN, a neural vocoder used in conjunction with text-to-speech models like Tacotron for generating high-quality speech from text.","readme_excerpt":"# Installation\n\nEnsure you have:\n\n* Python >= 3.6\n* [Pytorch 1 with CUDA](https://pytorch.org/)\n\nThen install the rest with pip:\n\n> pip install -r requirements.txt\n\n---\n\n### Quick Start\n\nIf you want to use TTS functionality immediately you can simply use:\n\n> python quick_start.py\n\nThis will generate everything in the default sentences.txt file and output to a new 'quick_start' folder where you can playback the wav files and take a look at the attention plots\n\nYou can also use that script to generate custom tts sentences and/or use '-u' to generate unbatched (better audio quality):\n\n> python quick_start.py -u --input_text \"What will happen if I run this command?\"","github_created_at":"2018-03-16T14:03:52+00:00","created_at":"2026-07-11T12:09:16.542958+00:00","updated_at":"2026-07-29T18:00:28.448897+00:00","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":"neural-vocoder","name":"neural-vocoder"},{"slug":"pytorch","name":"pytorch"},{"slug":"speech-synthesis","name":"speech-synthesis"},{"slug":"tacotron","name":"tacotron"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"tts","name":"tts"},{"slug":"wavernn","name":"wavernn"}],"trust":{"provenance":{"is_fork":false,"github_id":125524069,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-29T18:00:27.599Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1488,"last_release_at":null},"security_summary":{"status":"ok","scanner":"osv@v1","low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:09:18.612Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-29T18:00:28.080Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-29T18:00:28.080Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-29T18:00:28.080Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Python version must be equal to or higher than 3.6","Pytorch 1 with CUDA support is a prerequisite"],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["When you require a compact and efficient method to produce natural-sounding speech synthesis, specifically with the need for high fidelity in audio quality.","If your project already utilizes PyTorch, leveraging WaveRNN can streamline integration due to its dependency on this framework."],"when_not_to_use":["Avoid using when you need extensive customization of the vocoder parameters, since it is optimized for specific configurations and might not offer the level of tweakability other frameworks provide.","Not recommended if your setup does not support CUDA, as WaveRNN requires PyTorch with CUDA for execution."],"source":"enrich:decision_facts","observed_at":"2026-07-17T01:09:53.980Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Python version must be equal to or higher than 3.6; Pytorch 1 with CUDA support is a prerequisite"},{"label":"Adopt for","value":"WaveRNN is a Python-based neural vocoder that can generate high-quality speech from text when used with TTS models like Tacotron."}]}}