{"apiVersion":"v1","taxonomyVersion":1,"generatedAt":"2026-10-29T18:12:03.065Z","data":{"recordId":"wsa_zz3em246hqat","score":0.862,"confidence":"high","capped":false,"capReason":null,"sources":[{"n":1,"url":"https://huggingface.co/Aratako/Irodori-TTS-v4-Large","publisher":"Hugging Face","authority":"owner-controlled","verification":"verified","lastRetrievedAt":"2026-10-28T00:02:38.647Z","detectedPublishedAt":"2026-09-27T12:21:00.000Z","rights":"original"}],"claims":[{"id":"f07d0e92-d0dd-43a1-a3bc-aca2ef32f5a4","kind":"capability","statement":"The model supports Japanese text-to-speech, zero-shot voice cloning, text-based voice design, and style-controlled voice cloning.","citations":[{"source":1,"supportProbability":0.96,"supports":true,"quote":{"text":"It combines **Text (Input) + Reference Speech + Caption Text** in a unified model, enabling zero-shot voice cloning, text-based voice design, and style-controlled voice cloning.","rights":"original"}}]},{"id":"d696441a-140e-4ec3-bfbb-343c0072bb51","kind":"capability","statement":"It accepts up to 120 seconds of combined reference audio.","citations":[{"source":1,"supportProbability":0.97,"supports":true,"quote":{"text":"* **Long-reference Voice Cloning:** Condition generation on one or more reference clips, with up to 120 seconds of combined reference audio.","rights":"original"}}]},{"id":"b0bed0d4-42c6-4271-a8a1-644f3d161824","kind":"capability","statement":"Emojis in the input text can control speaking styles, emotions, and non-verbal vocal expressions.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"By inserting specific emojis into the input text, you can control speaking styles, emotions, and non-verbal vocal expressions in the generated audio.","rights":"original"}}]},{"id":"267d34ec-c570-4ed1-9304-ba3a44a3e4e7","kind":"capability","statement":"SilentCipher is integrated to apply invisible audio watermarks to generated outputs.","citations":[{"source":1,"supportProbability":0.99,"supports":true,"quote":{"text":"* **Integrated Watermarking:** Integrates [SilentCipher](https://github.com/sony/silentcipher) to apply robust, invisible audio watermarks directly to generated outputs, promoting responsible AI usage.","rights":"original"}}]},{"id":"2b2c181c-515d-4314-8833-b84ed4b1fe7c","kind":"availability","statement":"The model is available on Hugging Face, with inference code and installation instructions linked from its GitHub repository.","citations":[{"source":1,"supportProbability":0.6,"supports":false,"quote":{"text":"For inference code, installation instructions, and training scripts, please refer to the GitHub repository:","rights":"original"}}]},{"id":"4ad604a9-ef95-43ba-a7a1-740258b9b4d9","kind":"recommendation-relevant","statement":"The model supports Japanese text input only.","citations":[{"source":1,"supportProbability":0.98,"supports":true,"quote":{"text":"- **Japanese Only:** This model currently supports Japanese text input only.","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."}}}