Third-party notices for VoxDNA.

Tears of Steel

Purpose: Demo video footage used in edited web demonstrations
License: Creative Commons Attribution 3.0 (CC BY 3.0)

Distribution note: Original film by Blender Foundation / Mango Open Movie Project. Edited excerpts may appear in VoxDNA website demo videos.

Source: https://mango.blender.org/

OpenAI Whisper

Purpose: Speech transcription
License: MIT

Source: https://github.com/openai/whisper

Demucs

Purpose: Voice separation
License: MIT

Source: https://github.com/facebookresearch/demucs

Resemblyzer

Purpose: Voice identity embedding and speaker matching support
License: Apache-2.0

Source: https://github.com/resemble-ai/Resemblyzer

omote-ai/distilhubert-ser

Purpose: Emotion analysis
License: MIT on the model card

Source: https://huggingface.co/omote-ai/distilhubert-ser

pyannote speaker-diarization-3.1

Purpose: Speaker diarization pipeline
License: MIT on the model card

Distribution note: Distributed as part of the VoxDNA AI pack for activated license holders. The upstream source is a gated Hugging Face resource, and public open-mirror distribution is not used in the VoxDNA delivery flow.

Source: https://huggingface.co/pyannote/speaker-diarization-3.1

pyannote segmentation-3.0

Purpose: Segmentation model used by the diarization pipeline
License: MIT on the model card

Distribution note: Distributed as part of the VoxDNA AI pack for activated license holders. The upstream source is a gated Hugging Face resource, and public open-mirror distribution is not used in the VoxDNA delivery flow.

Source: https://huggingface.co/pyannote/segmentation-3.0

pyannote/wespeaker-voxceleb-resnet34-LM

Purpose: Speaker embedding model referenced by the local diarization pipeline
License: CC-BY-4.0

Distribution note: Upstream attribution should travel with the AI pack distribution and any notice files that describe bundled model assets.

Source: https://huggingface.co/pyannote/wespeaker-voxceleb-resnet34-LM