{"data":{"slug":"tensorspeech-tensorflowtts","name":"TensorFlowTTS","tagline":"Real-Time State-of-the-art Speech Synthesis for Tensorflow 2","github_url":"https://github.com/TensorSpeech/TensorFlowTTS","owner":"TensorSpeech","repo":"TensorFlowTTS","owner_avatar_url":"https://avatars.githubusercontent.com/u/67569298?v=4","primary_language":"Python","stars":3993,"forks":798,"topics":["chinese-tts","fastspeech","fastspeech2","german-tts","japanese-tts","korea-tts","melgan","mobile-tts","multi-speaker-tts","multiband-melgan","parallel-wavegan","real-time","speech-synthesis","tacotron2","tensorflow2","text-to-speech","tflite","tts","vocoder","zh-tts"],"archived":false,"github_pushed_at":"2024-07-05T07:24:49+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/tensorspeech-tensorflowtts","markdown_url":"https://www.graphcanon.com/tools/tensorspeech-tensorflowtts.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tensorspeech-tensorflowtts","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tensorspeech-tensorflowtts","description":":stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)","homepage_url":"https://tensorspeech.github.io/TensorFlowTTS/","license":"Apache-2.0","open_issues":2,"watchers":75,"ai_summary":"TensorFlowTTS is a real-time speech synthesis toolkit supporting multiple languages including English, French, Korean, Chinese, and German.","readme_excerpt":"## Requirements\nThis repository is tested on Ubuntu 18.04 with:\n\n- Python 3.7+\n- Cuda 10.1\n- CuDNN 7.6.5\n- Tensorflow 2.2/2.3/2.4/2.5/2.6\n- [Tensorflow Addons](https://github.com/tensorflow/addons) >= 0.10.0\n\nDifferent Tensorflow version should be working but not tested yet. This repo will try to work with the latest stable TensorFlow version. **We recommend you install TensorFlow 2.6.0 to training in case you want to use MultiGPU.**\n\n---\n\n# License\nAll models here are licensed under the [Apache 2.0](http://www.apache.org/licenses/LICENSE-2.0)","github_created_at":"2020-03-22T03:44:10+00:00","created_at":"2026-07-11T12:07:21.107588+00:00","updated_at":"2026-07-29T12:00:32.951642+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":"chinese-tts","name":"chinese-tts"},{"slug":"fastspeech","name":"fastspeech"},{"slug":"fastspeech2","name":"fastspeech2"},{"slug":"german-tts","name":"german-tts"},{"slug":"japanese-tts","name":"japanese-tts"},{"slug":"korea-tts","name":"korea-tts"},{"slug":"melgan","name":"melgan"},{"slug":"mobile-tts","name":"mobile-tts"}],"trust":{"provenance":{"is_fork":false,"github_id":249107601,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-29T12:00:31.117Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":754,"last_release_at":"2021-08-21T13:46:37Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:07:30.120Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-29T12:00:31.657Z"},"deploy":{"source":"dockerfile:docker-compose.yml","self_host":true,"observed_at":"2026-07-29T12:00:31.657Z","managed_saas":false},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-29T12:00:31.657Z"},"has_docker":{"value":true,"source":"dockerfile:docker-compose.yml","observed_at":"2026-07-29T12:00:31.657Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-29T12:00:31.657Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need state-of-the-art real-time text-to-speech functionality across several languages including English, French, Korean, Chinese, German,","If your project requires the compatibility of TensorFlow 2.x for further integration or leveraging multi-GPU setups, especially with version 2.6 recommended by the developers for optimal performance"],"when_not_to_use":["When you require a text-to-speech solution that works on operating systems other than Ubuntu 18.04 as it has been tested only on this specific environment","If your project cannot meet the hardware requirements such as needing CUDA 10.1 and CuDNN 7.6.5, or if you want to avoid dependency on TensorFlow-specific packages like TensorFlow Addons"],"source":"enrich:decision_facts","observed_at":"2026-07-16T22:06:32.082Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"TensorFlowTTS is notable for its real-time speech synthesis capabilities with support for multiple languages and advanced models like Tacotron2, FastSpeech2, MelGAN."}]}}