署名

人声与语音模型

• The fr_claire voice was trained on the SIWIS French Speech Synthesis Database by Pierre-Edouard Honnet, Alexandros Lazaridis, Philip N. Garner and Junichi Yamagishi (Idiap Research Institute), licensed under CC BY 4.0; modified.

  CC BY 4.0 · SIWIS French Speech Synthesis Database

• Built on Qwen3-TTS by the Qwen team, Alibaba Cloud, licensed under the Apache License 2.0; modified (fine-tuned) by 2hives.

  Apache License 2.0 · Qwen3-TTS

• Kokoro-82M by hexgrad, licensed under the Apache License 2.0. Kokoro-82M includes SIWIS French (CC BY 4.0, Honnet et al. 2017) and Koniwa (CC BY 3.0) data.

  Apache License 2.0 · Kokoro-82M · CC BY 3.0

• Voice 'Sohee' from Qwen3-TTS (CustomVoice) by the Qwen team, Alibaba Cloud, licensed under the Apache License 2.0; used unmodified.

  Apache License 2.0 · Qwen3-TTS CustomVoice

• Chatterbox by Resemble AI, Copyright (c) 2025 Resemble AI, licensed under the MIT License. Its output carries Resemble's inaudible Perth watermark.

  MIT License · Chatterbox

• AudioSeal (Meta AI), licensed under the MIT License, marks synthetic audio. SpeechBrain (spkrec-ecapa-voxceleb), licensed under the Apache License 2.0, checks speaker consent. Whisper (OpenAI) and faster-whisper (SYSTRAN), licensed under the MIT License, check recordings.

  AudioSeal · SpeechBrain · Whisper · faster-whisper

用于训练的语音录音

• Contains Multilingual LibriSpeech (Pratap et al., Interspeech 2020), CC BY 4.0, derived from LibriVox public-domain recordings.

  Multilingual LibriSpeech · CC BY 4.0

• Contains audio from the European Parliament (© European Union), via VoxPopuli (Meta AI, CC0).

  VoxPopuli · European Parliament legal notice

• Voice data: CSS10 (Park & Mulc, Interspeech 2019), from LibriVox public-domain recordings. With thanks to the LibriVox volunteers.

  CSS10 · LibriVox

• Voice data: Open Home Foundation / Nabu Casa voice-datasets (CC0).

  OHF voice-datasets · CC0 1.0

环境音

播放器混音面板中的部分环境音是以知识共享署名许可共享的录音：

• "250730_055349_PH_Ocean_waves_at_White_Beach" by kevp888 (https://freesound.org/people/kevp888/sounds/829444/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), modified: trimmed, looped, levelled.

• "strong wind river-side 121226_03.flac" by klankbeeld (https://freesound.org/people/klankbeeld/sounds/172522/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), modified: trimmed, looped, levelled.

• "small running water forest stream_1.wav" by Kranhytt (https://freesound.org/people/Kranhytt/sounds/671883/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), modified: trimmed, looped, levelled.

• "020A_100111_0243_EXP02_Bells_drone" by kevp888 (https://freesound.org/people/kevp888/sounds/844152/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), modified: trimmed, looped, levelled.

• "waves seadike NL 3.46pm 230519_0608" by klankbeeld (https://freesound.org/people/klankbeeld/sounds/688082/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), modified: trimmed to 40 min, levelled, re-encoded.

• "1 Hour of Relaxing fireplace with Crackling Sounds" by Hear_it_use_it (https://freesound.org/people/Hear_it_use_it/sounds/873471/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), modified: trimmed to 40 min, levelled, re-encoded.

• "FirePlace_SetExtendedMeditationTrack.mp3" by Glen_Hoban (https://freesound.org/people/Glen_Hoban/sounds/459935/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), modified: trimmed to 40 min, levelled, re-encoded.

• "Audio-Based identification of Beehive states: The dataset" by Ines Nolasco, Alessandro Terenzi, Stefania Cecchi, Simone Orcioni, Helen L. Bear and Emmanouil Benetos (https://doi.org/10.5281/zenodo.2667806), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), modified: trimmed to 40 min, five files joined with crossfades, levelled, re-encoded. Dataset authors request citing: Nolasco et al., "Audio-based identification of beehive states", ICASSP 2019, pp. 8256-8260.

每个人声来自哪里