Video, audio and subtitle production

Turn a photo reference and creative request into an assembled video with sound, subtitles and versions for different screen shapes.

Tencent · Singapore · 27 March 2026

Taking a video request through production

OpenClaw's Tencent Media Processing Service skill coordinated generation, audio, stitching and subtitles through a beta connection. Hailuo, Kling and Hunyuan were among the tools showcased. Finished media returned through Telegram for the creator to review.

Generation and assembly

The assistant waited for cloud jobs, retrieved finished clips and assembled the output. The portrait version normalised opening, interlude and closing clips before joining them with a consistent soundtrack.

Reusing edits or generating fresh footage

A square crop reused completed footage. A changed facial reference required fresh clips before assembly, generated sequentially to avoid concurrency issues.

Delivery after the dependent jobs finish

Signed download links provided access to cloud outputs for dependent edits and Telegram delivery.

Resources

All work