[ { "file": "reservation.wav", "description": "Original authored Japanese text synthesized using Mei voice", "voice": "mei_normal.htsvoice", "creator": "Nagoya Institute of Technology / MMDAgent project", "license": "CC-BY-3.0", "source": "https://www.mmdagent.jp/", "changes": "Synthesized speech, mono 16kHz WAV" }, { "file": "music-639.wav", "license": "CC0-1.0", "creator": "memexikon", "license_url": "http://creativecommons.org/publicdomain/zero/1.0/", "source_url": "https://freesound.org/people/memexikon/sounds/639/", "title": "lockjawnetf.wav", "changes": "None; original source WAV" }, { "file": "animal-dog-birds-238688.wav", "creator": "SoundEnsemble", "title": "SE ANIMALS dog barking birds.wav", "source_url": "https://freesound.org/people/SoundEnsemble/sounds/238688/", "preview_url": "https://cdn.freesound.org/previews/238/238688_3662372-hq.mp3", "license": "CC0-1.0", "license_url": "https://creativecommons.org/publicdomain/zero/1.0/", "license_verified": "2026-09-20", "changes": "Freesound high-quality preview decoded, downmixed to mono, and resampled to 16 kHz PCM WAV; full 22.248688-second recording retained.", "source_sha256": "c2e6ea3ebff38bb72c57831da11e22fb606b845e9bd6085155e43dc64be788f9", "sha256": "cb229bbe56c08902fb2e1e1d7bad639b49908148e384bdf3a1aa8d9687b19c24", "source_id_audit": "freesound:238688 was absent from local FSD50K and typed-audio manifests at selection time.", "selection_note": "Selected from its dog-and-birds description and CC0 license before inference; no model output was used to choose it. Exclude this demo from future independent evaluation." }, { "file": "irodori-reservation.wav", "text": "明日の夜七時に、二人で予約をお願いできますか。", "expected_intent": "reservation", "synthetic_audio": true, "model": "Aratako/Irodori-TTS-500M-v3", "revision": "236c1e56591279fc24e3c1bf6609fc06e48dde28", "source_code_revision": "eaf74d6a19138f743acb5b71a445fd25a57db987", "seed": 913, "num_steps": 40, "reference_audio": null, "watermark_enabled": true, "sample_rate": 48000, "seconds": 4.0, "generation_seconds": 0.9263423918746412, "license": "MIT", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-500M-v3", "creator": "MocoVoice; synthesized with Irodori-TTS by Chihiro Arata", "sha256": "8f8ee91977655e119b26d3d7d35e9b414e62f1ef9c6b2c46097f010442f61fd9" }, { "file": "irodori-change.wav", "text": "すみません、予約を土曜日の午後三時に変更したいのですが。", "expected_intent": "change", "synthetic_audio": true, "model": "Aratako/Irodori-TTS-500M-v3", "revision": "236c1e56591279fc24e3c1bf6609fc06e48dde28", "source_code_revision": "eaf74d6a19138f743acb5b71a445fd25a57db987", "seed": 271, "num_steps": 40, "reference_audio": null, "watermark_enabled": true, "sample_rate": 48000, "seconds": 4.72, "generation_seconds": 0.4987814510241151, "license": "MIT", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-500M-v3", "creator": "MocoVoice; synthesized with Irodori-TTS by Chihiro Arata", "sha256": "5c3fe27ad38a581e1f545c6cc8b18f8dd7a75b24e7c2737952e3b0e88ae589c2" }, { "file": "irodori-cancel.wav", "text": "急な予定が入ってしまったので、明日の予約をキャンセルしてください。", "expected_intent": "cancel", "synthetic_audio": true, "model": "Aratako/Irodori-TTS-500M-v3", "revision": "236c1e56591279fc24e3c1bf6609fc06e48dde28", "source_code_revision": "eaf74d6a19138f743acb5b71a445fd25a57db987", "seed": 614, "num_steps": 40, "reference_audio": null, "watermark_enabled": true, "sample_rate": 48000, "seconds": 4.88, "generation_seconds": 0.49401673721149564, "license": "MIT", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-500M-v3", "creator": "MocoVoice; synthesized with Irodori-TTS by Chihiro Arata", "sha256": "25945f9ea6923cb47a1b008e0dbe935e4ee30bb3a30a1a030c12817b6a693b01" }, { "file": "natural-reservation-a.wav", "intent": "reservation", "variant": "a", "text": "こんばんは。あしたの夜、しちじごろに二人でお願いしたいんですけど、まだ空いてますか？", "caption": "落ち着いた大人の話者。予約の電話で、相手に配慮しながら、自然な会話の速さでやわらかく話す。文の切れ目では短く息をつぎ、丁寧だが読み上げ調にならない。", "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "model_card_license_verified": "2026-09-20", "source_code_revision": "unversioned-worktree", "seed": 1081, "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 8.44, "peak_abs": 0.9765087366104126, "rms": 0.1376929726771456, "generation_seconds": 1.1542682349681854, "sha256": "bf9ce6d83ae7fe8961f97f4cd95a7d6be1ca29d2c373cc77c96b7a41d7d719d2", "integrity_note": "Duration, peak, RMS, and SHA-256 are file checks only; they do not measure naturalness.", "provenance_note": "Text-plus-caption-only synthesis; no real-person reference audio or voice embedding supplied." }, { "file": "natural-change-a.wav", "intent": "change", "variant": "a", "text": "すみません、予約のことなんですけど。土曜日の午後、さんじに変更できますか？", "caption": "穏やかで親しみのある大人の話者。予約内容の変更を電話で相談している。急がず自然な間を取り、控えめにお願いする会話らしい口調。", "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "model_card_license_verified": "2026-09-20", "source_code_revision": "unversioned-worktree", "seed": 2081, "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 6.64, "peak_abs": 0.7287325859069824, "rms": 0.1640570232803877, "generation_seconds": 0.627793378662318, "sha256": "a1a9828f1beada7c90182df61d30872a5edc056bef833219fd53fc48ee243a2d", "integrity_note": "Duration, peak, RMS, and SHA-256 are file checks only; they do not measure naturalness.", "provenance_note": "Text-plus-caption-only synthesis; no real-person reference audio or voice embedding supplied." }, { "file": "natural-cancel-b.wav", "intent": "cancel", "variant": "b", "text": "すみません、急に予定が入ってしまって…。あしたの予約、キャンセルをお願いできますか？", "caption": "落ち着いた大人の話者。予定変更を申し訳なく思いながら、予約のキャンセルを電話で伝える。小さなためらいと自然な息継ぎがあり、丁寧でやわらかい口調。", "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "model_card_license_verified": "2026-09-20", "source_code_revision": "unversioned-worktree", "seed": 3082, "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 8.96, "peak_abs": 0.8194587230682373, "rms": 0.1417061149254557, "generation_seconds": 0.7651458447799087, "sha256": "52f0ed8dfd7ef2cbdd0ce67533f4f1acf2fe7ced93c9e34aa5d49957609f35dc", "integrity_note": "Duration, peak, RMS, and SHA-256 are file checks only; they do not measure naturalness.", "provenance_note": "Text-plus-caption-only synthesis; no real-person reference audio or voice embedding supplied." }, { "id": "order-full", "name": "注文を最後まで伝える", "speech_act": "request", "intent": "order", "turn_complete": true, "context": "店員: ご注文が決まりましたら、お声がけください。", "text": "きのこのパスタを一つ、持ち帰りでお願いします。", "caption": "落ち着いた大人の話者。店員に注文を伝える短い会話。自然な速さで、最後まで言い切る。", "seed": 4101, "file": "turn-order-full.wav", "expected": { "speech_act": "request", "intent": "order", "turn_complete": true }, "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "training_excluded": true, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "license_evidence": "spaces/mocovoice-audio-jev/licenses/irodori-model-card.md", "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 4.08, "peak_abs": 0.7851645946502686, "rms": 0.17343387180324984, "generation_seconds": 0.9514303421601653, "sha256": "1cd199edb025dc5e93bb8ef22dc8cb98297ea879ee30e578bef43cd2c0260618", "provenance_note": "Original authored text and caption-only VoiceDesign synthesis; no reference audio, embedding, or speaker identity supplied.", "annotation_caveat": "turn_complete is an authored semantic-endpoint annotation. It does not prove a model can make arbitrary floor-taking or turn-taking predictions." }, { "id": "backchannel-full", "name": "相手の説明への相づち", "speech_act": "backchannel", "intent": "none", "turn_complete": true, "context": "案内係: 入口を出たら右へ進むと、受付が見えてきます。", "text": "うん、分かりました。", "caption": "親しみのある大人の話者。相手の説明を聞きながら短く相づちを打つ。急がず、自然に言い切る。", "seed": 4102, "file": "turn-backchannel-full.wav", "expected": { "speech_act": "backchannel", "intent": "none", "turn_complete": true }, "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "training_excluded": true, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "license_evidence": "spaces/mocovoice-audio-jev/licenses/irodori-model-card.md", "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 4.24, "peak_abs": 0.7609981894493103, "rms": 0.15303109302071377, "generation_seconds": 0.544307358097285, "sha256": "ab9c4c35fa15521b227540689743c15db1fae9a4701cd1c22069fe0789ac844d", "provenance_note": "Original authored text and caption-only VoiceDesign synthesis; no reference audio, embedding, or speaker identity supplied.", "annotation_caveat": "turn_complete is an authored semantic-endpoint annotation. It does not prove a model can make arbitrary floor-taking or turn-taking predictions." }, { "id": "confirm-full", "name": "内容を確認して承認する", "speech_act": "confirm", "intent": "reservation", "turn_complete": true, "context": "店員: 来週の火曜日、午後六時に二名様でお席をお取りしてよろしいですか。", "text": "はい、その内容でお願いします。", "caption": "穏やかな大人の話者。店員の確認に簡潔に同意する。会話らしい自然な間で、やわらかく言い切る。", "seed": 4103, "file": "turn-confirm-full.wav", "expected": { "speech_act": "confirm", "intent": "reservation", "turn_complete": true }, "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "training_excluded": true, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "license_evidence": "spaces/mocovoice-audio-jev/licenses/irodori-model-card.md", "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 3.16, "peak_abs": 0.6248125433921814, "rms": 0.15614677213260153, "generation_seconds": 0.49432186922058463, "sha256": "5c9569279a31be36d519b3e9e924e187d29e3eba967ed70850915108e4590e51", "provenance_note": "Original authored text and caption-only VoiceDesign synthesis; no reference audio, embedding, or speaker identity supplied.", "annotation_caveat": "turn_complete is an authored semantic-endpoint annotation. It does not prove a model can make arbitrary floor-taking or turn-taking predictions." }, { "id": "correction-full", "name": "日付を訂正して変更する", "speech_act": "correct", "intent": "change", "turn_complete": true, "context": "店員: ご予約は金曜日の午後三時で承っています。", "text": "あ、すみません。金曜日ではなく、土曜日の午後に変更をお願いします。", "caption": "丁寧な大人の話者。予約内容を思い出して訂正する。最初に短いためらいを置き、最後ははっきり言い切る。", "seed": 4104, "file": "turn-correction-full.wav", "expected": { "speech_act": "correct", "intent": "change", "turn_complete": true }, "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "training_excluded": true, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "license_evidence": "spaces/mocovoice-audio-jev/licenses/irodori-model-card.md", "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 6.4, "peak_abs": 0.7035095691680908, "rms": 0.1609569216640416, "generation_seconds": 0.6292441417463124, "sha256": "b73eb1847645cd473f71a8d8296639f6bc38ec17dc628ec843a680d005d44a1c", "provenance_note": "Original authored text and caption-only VoiceDesign synthesis; no reference audio, embedding, or speaker identity supplied.", "annotation_caveat": "turn_complete is an authored semantic-endpoint annotation. It does not prove a model can make arbitrary floor-taking or turn-taking predictions." }, { "id": "cancel-full", "name": "注文を取り消す", "speech_act": "cancel", "intent": "cancel", "turn_complete": true, "context": "店員: 先ほどのスープとコーヒーのご注文を確認します。", "text": "すみません、スープのほうは取り消してください。", "caption": "落ち着いた大人の話者。注文の一部を丁寧に取り消す。自然な会話の速さで、申し訳なさを少し含めて言い切る。", "seed": 4105, "file": "turn-cancel-full.wav", "expected": { "speech_act": "cancel", "intent": "cancel", "turn_complete": true }, "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "training_excluded": true, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "license_evidence": "spaces/mocovoice-audio-jev/licenses/irodori-model-card.md", "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 3.44, "peak_abs": 0.781799852848053, "rms": 0.16470869580552724, "generation_seconds": 0.5071098008193076, "sha256": "24ca56ecc4191620c37834cf5d2f28c51ed7192ee5b6235585fb2dcc0ed38045", "provenance_note": "Original authored text and caption-only VoiceDesign synthesis; no reference audio, embedding, or speaker identity supplied.", "annotation_caveat": "turn_complete is an authored semantic-endpoint annotation. It does not prove a model can make arbitrary floor-taking or turn-taking predictions." }, { "id": "order-hesitation-unfinished", "name": "迷って途中で止まる注文", "speech_act": "request", "intent": "order", "turn_complete": false, "context": "店員: ご注文が決まりましたら、お声がけください。", "text": "きのこのパスタを一つ、ええと、持ち帰りにするか…", "caption": "迷っている大人の話者。注文を考えながら言いよどみ、答えを決めずに途中で止める。読み上げ調にしない。", "seed": 4106, "file": "turn-order-hesitation-unfinished.wav", "expected": { "speech_act": "request", "intent": "order", "turn_complete": false }, "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "training_excluded": true, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "license_evidence": "spaces/mocovoice-audio-jev/licenses/irodori-model-card.md", "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 5.08, "peak_abs": 0.9923233389854431, "rms": 0.161138963203946, "generation_seconds": 0.5771061358973384, "sha256": "70c4bc0af49280d772c09ea9977f5a1d072f58c71705be9dc36bd1704010ea1e", "provenance_note": "Original authored text and caption-only VoiceDesign synthesis; no reference audio, embedding, or speaker identity supplied.", "annotation_caveat": "turn_complete is an authored semantic-endpoint annotation. It does not prove a model can make arbitrary floor-taking or turn-taking predictions." }, { "id": "reservation-clause-unfinished", "name": "意味のある途中節で止まる予約", "speech_act": "request", "intent": "reservation", "turn_complete": false, "context": "店員: ご希望の日時と人数をお知らせください。", "text": "あしたの夕方に二人で、もし窓際が…", "caption": "控えめな大人の話者。予約の条件を伝え始めるが、文を完結させずに意味のある途中で止まる。自然な短い間を含める。", "seed": 4107, "file": "turn-reservation-clause-unfinished.wav", "expected": { "speech_act": "request", "intent": "reservation", "turn_complete": false }, "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "training_excluded": true, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "license_evidence": "spaces/mocovoice-audio-jev/licenses/irodori-model-card.md", "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 5.28, "peak_abs": 1.0007697343826294, "rms": 0.13793335127204556, "generation_seconds": 0.5772101040929556, "sha256": "14de328d4e6a4271e671967333fc0c5392d637d0a9876c7b6d0d72a1eb4fa926", "provenance_note": "Original authored text and caption-only VoiceDesign synthesis; no reference audio, embedding, or speaker identity supplied.", "annotation_caveat": "turn_complete is an authored semantic-endpoint annotation. It does not prove a model can make arbitrary floor-taking or turn-taking predictions." }, { "id": "reservation-full-contrast", "name": "同じ予約条件を最後まで伝える", "speech_act": "request", "intent": "reservation", "turn_complete": true, "context": "店員: ご希望の日時と人数をお知らせください。", "text": "あしたの夕方に二人で、窓際の席を予約したいです。", "caption": "控えめな大人の話者。予約の条件を伝え、最後まで自然に言い切る。文の区切りに短い息継ぎを入れる。", "seed": 4108, "file": "turn-reservation-full-contrast.wav", "expected": { "speech_act": "request", "intent": "reservation", "turn_complete": true }, "synthetic_audio": true, "reference_audio": null, "reference_embedding": null, "training_excluded": true, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_card_license": "MIT", "license_evidence": "spaces/mocovoice-audio-jev/licenses/irodori-model-card.md", "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "watermark_enabled": true, "sample_rate": 48000, "seconds": 5.68, "peak_abs": 0.8254440426826477, "rms": 0.15123665222928692, "generation_seconds": 0.5876368628814816, "sha256": "36a84d9c7061577b438529f4e0882d456f7f3ce773cc9f55248be5fcac1a43a3", "provenance_note": "Original authored text and caption-only VoiceDesign synthesis; no reference audio, embedding, or speaker identity supplied.", "annotation_caveat": "turn_complete is an authored semantic-endpoint annotation. It does not prove a model can make arbitrary floor-taking or turn-taking predictions." }, { "file": "adult-reservation-v3.wav", "kind": "reservation", "text": "もしもし、あしたの夜七時に、二人で予約できますか。", "caption": "40代の成人男性の中低音の声。飾らない日常会話。抑揚は小さく、落ち着いた普通の話し方。語尾を伸ばさず、力を抜いて自然に話す。", "seed": 5712, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "reference_audio": null, "synthetic_audio": true, "training_excluded": true, "watermark_enabled": true, "sample_rate": 48000, "seconds": 4.56, "max_seconds": 8.0, "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "generation_seconds": 0.5680867279879749, "peak": 0.9645974040031433, "rms": 0.15562847256660461, "sha256": "e494ae99d12c8fd23ba4741a5a8507942f0e54877b1c43493d5924e0a03c7585", "license": "MIT", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "review_note": "Caption specifies voice style. No perceptual listening claim.", "source_file": "reservation-5712.wav", "creator": "mocomoco inc.; synthesized with Irodori VoiceDesign by Chihiro Arata" }, { "file": "adult-backchannel-v3.wav", "kind": "backchannel", "text": "ああ、そうなんですね。", "caption": "40代の成人男性の中低音の声。飾らない日常会話。抑揚は小さく、落ち着いた普通の話し方。語尾を伸ばさず、力を抜いて自然に話す。", "seed": 5701, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "reference_audio": null, "synthetic_audio": true, "training_excluded": true, "watermark_enabled": true, "sample_rate": 48000, "seconds": 3.48, "max_seconds": 3.5, "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "generation_seconds": 0.9337333729490638, "peak": 0.8861069679260254, "rms": 0.12877875566482544, "sha256": "424c3152da9a8b1444363ff71574cfe26c855b5fe65e22ab6a553530132bdbe5", "license": "MIT", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "review_note": "Caption specifies voice style. No perceptual listening claim.", "source_file": "backchannel-5701.wav", "creator": "mocomoco inc.; synthesized with Irodori VoiceDesign by Chihiro Arata" }, { "file": "adult-cancel-v3.wav", "kind": "cancel", "text": "すみません、あしたの予約をキャンセルしたいんですけど。", "caption": "40代の成人男性の中低音の声。飾らない日常会話。抑揚は小さく、落ち着いた普通の話し方。語尾を伸ばさず、力を抜いて自然に話す。", "seed": 5721, "model": "Aratako/Irodori-TTS-600M-v3-VoiceDesign", "model_revision": "e863a3a93e652e09afeff3e84823a206a0a60314", "reference_audio": null, "synthetic_audio": true, "training_excluded": true, "watermark_enabled": true, "sample_rate": 48000, "seconds": 3.92, "max_seconds": 8.0, "num_steps": 40, "cfg_scale_text": 3.0, "cfg_scale_caption": 2.5, "cfg_guidance_mode": "independent", "generation_seconds": 0.511951609980315, "peak": 0.9111555218696594, "rms": 0.14880435168743134, "sha256": "27a758e3f6db7c2553db937a638f1ddf60e9ad79d3c5f49a8d8097480005dd99", "license": "MIT", "model_card": "https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign", "review_note": "Caption specifies voice style. No perceptual listening claim.", "source_file": "cancel-5721.wav", "creator": "mocomoco inc.; synthesized with Irodori VoiceDesign by Chihiro Arata" }, { "file": "music-acoustic-loop-848704.wav", "creator": "EEE3333E", "title": "Acoustic Guitar loop", "source_url": "https://freesound.org/people/EEE3333E/sounds/848704/", "preview_url": "https://cdn.freesound.org/previews/848/848704_17604172-hq.mp3", "license": "CC0-1.0", "license_url": "https://creativecommons.org/publicdomain/zero/1.0/", "license_verified": "2026-09-20", "changes": "Freesound high-quality preview decoded, downmixed to mono, and resampled to 16 kHz PCM WAV; full 16.045-second loop retained.", "source_sha256": "93a4c8a5c06977e94b22a41a280aa3360bd7f1f61ecf68cb5cc66e76f0ffa390", "sha256": "c851b6cad67ac9ef08f5c634efb90f001670f5ed454320c276310bfe9b7c020a", "source_id_audit": "freesound:848704 was absent from local FSD50K and typed-audio manifests at selection time.", "selection_note": "Selected from its acoustic-guitar-loop description and CC0 license before inference; no model output was used to choose it. Exclude this demo from future independent evaluation." } ]