TalkingAvatar generates expressive, lip-synchronized avatar videos from a reference image, speech audio, and an optional text prompt. Model weights are distributed as sharded safetensors with an integrity manifest and runtime configuration.

Source Code | Training Dataset | Neosapience | Typecast

TalkingAvatar was trained using the TA2.0 Animation Dataset. See the dataset repository for its documentation, structure, and access details.

Clone the source repository and create its uv environment:

Generate a video with the top-level inference script:

The script downloads the TalkingAvatar checkpoint and resolves its required video and audio dependencies through the Hugging Face cache. Run python inference.py --help for all options.

The runtime automatically chooses the shortest model-valid frame count that covers the complete input audio. --frame_num remains available as an override.

TalkingAvatar is intended for research, evaluation, and authorized creative work with audio-driven avatars. Use only images and voices for which you have the necessary consent and rights, and disclose generated media where appropriate.

Output quality and lip synchronization vary with pose, occlusion, audio quality, language, and image domain. The runtime does not provide identity verification, consent management, watermarking, or content moderation.

TalkingAvatar is released under the Apache License 2.0. See the source repository for complete license terms, third-party notices, and the full model card.

TalkingAvatar was developed as part of the 첨단 GPU 활용 지원 사업 (project period 2026-04-01 – 2026-07-15), supported by 정보통신산업진흥원 and 한국정보통신진흥협회.