{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T15:48:18.342Z","data":{"recordId":"wsa_dwcfvzpa4af9","score":0.975,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/inclusionAI/Ming-3.0-tts-tiny","publisher":"inclusionAI","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:39:38.860Z","detectedPublishedAt":"2026-09-22T12:46:28.000Z","rights":"original"}],"claims":[{"id":"12face46-787f-4e03-856a-3cbfb6dd616e","kind":"availability","statement":"The Hugging Face repository contains sharded weights and supporting model code, audio tokenizer, speaker encoder and text tokenizer.","citations":[{"source":1,"supportProbability":0.81,"supports":true,"quote":{"text":"The repository includes sharded weights, supporting model code, audio tokenizer, speaker encoder and text tokenizer.","rights":"original"}}]},{"id":"ac81107d-4997-4c92-9966-d7f8d5807357","kind":"capability","statement":"The model supports zero-shot voice cloning from a short reference clip.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- Zero-shot voice cloning from a short reference clip","rights":"original"}}]},{"id":"c63219f1-68d5-445d-8bda-3af45fcb1921","kind":"capability","statement":"It supports Chinese, English, German, Spanish, French, Korean and Japanese synthesis.","citations":[{"source":1,"supportProbability":0.95,"supports":true,"quote":{"text":"| Languages | Chinese, English, German, Spanish, French, Korean, Japanese |","rights":"original"}}]},{"id":"26526e38-b9d4-4bed-b44d-71b7b42e61fb","kind":"capability","statement":"It supports Sichuanese and Cantonese dialect control.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- Multilingual synthesis and Sichuanese/Cantonese dialect control","rights":"original"}}]},{"id":"52c6b68c-ce9b-4d4f-aeb5-a394515e3c22","kind":"capability","statement":"Speech delivery can be controlled with emotion, speed, pitch and volume settings.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"- Explicit emotion, speed, pitch and volume control","rights":"original"}}]},{"id":"9cbacf2e-24f6-4780-a454-5d79c714d2be","kind":"deployment","statement":"Inference requires cloning the Ming-3.0-tts GitHub repository and installing its dependencies.","citations":[{"source":1,"supportProbability":0.92,"supports":true,"quote":{"text":"> **Inference requires the [Ming-3.0-tts GitHub repository](https://github.com/inclusionAI/Ming-3.0-tts).** This Hugging Face repository is for checkpoint distribution and does not provide a standalone inference setup.","rights":"original"}}]}]},"nextCursor":null,"license":{"catalog":{"name":"CC BY 4.0","spdx":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","attribution":"wowsuchai","attributionUrl":"https://wowsuchai.withglint.app","covers":["catalog metadata","classifications","generated summaries","feed event metadata"]},"excluded":{"covers":["source quotations","linked source content"],"terms":"Not licensed by wowsuchai. Source quotations and linked source content keep their original rights."}}}