Generate lip-syncing VRM avatar video messages from text or audio as MP4 Telegram video notes.
npx skills add https://github.com/thewulf7/openclaw-avatarcam --skill video-message
Please help me install this Agent Skill. Skill: video-message Source: https://github.com/thewulf7/openclaw-avatarcam/tree/main/skill Command: npx skills add https://github.com/thewulf7/openclaw-avatarcam --skill video-message
Generate and send lip-syncing VRM avatar video messages from text or audio, enabling expressive replies and video-based TTS delivery.
Run avatarcam with an audio file or TTS input to generate a circular Telegram video note.
High-intent search queries and answers about installing and using this skill.
To generate a lip-sync avatar video message, you provide text or audio input to the Skill, which then renders a VRM avatar and outputs a 384x384 MP4 video note. This process enables expressive text-based video replies for messaging.
Yes, you can create Telegram video notes using a VRM avatar. The Skill specifically outputs 384x384 MP4 files in a circular format, which is the exact specification required for Telegram video notes.
Yes, you need both ffmpeg and avatarcam to render headless video messages. These dependencies are required by the Skill to process the audio or text input and generate the final VRM avatar lip-sync video output.
You can use a VRM avatar for TTS video delivery in OpenClaw by routing your text-to-speech audio through this Skill. It generates a lip-syncing avatar video that can be used as a video-based response within OpenClaw workflows.
Yes, you can configure the background when generating a lip-sync avatar video. The Skill supports configurable avatars and backgrounds, alongside optional headless rendering, allowing customized visual environments for your video messages.
A limitation of rendering VRM avatar video notes is the fixed output resolution of 384x384 MP4. Additionally, the Skill requires ffmpeg and avatarcam to be installed, meaning it cannot function without these specific external dependencies.
CastrozanOrchestrate VTuber avatar lip-sync, expressions, and audio routing via WebSocket API.
jykimConvert Deckset markdown slides with speaker notes into narrated MP4 videos.
GroundMountCompanyGenerate AI talking head videos with lip-sync using multiple model backends.
buda-aiConvert local video and audio files to MP4 with extracted audio and thumbnails.
