Talking heads & avatars: agent skills for AI avatar and talking head videos

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page.

AI avatars, lip sync, presenters, podcasts and dialogue videos. 27 skills for Claude Code, Codex and Grok, by type: workflows take a brief to a finished video, effects and styles change how it looks, prompts and guides teach the agent the craft, models run the generation.

How-to tutorials

• How to make a talking avatar video with AI: A person (from a headshot, or generated) speaks your script to camera with lip-sync, in any language.

Skills (27)

Effects (4)

• 3D Camera Captions — HeyGen: Captions that live in 3D around a talking head: the camera flies through the words, heroes pass behind the speaker.
• Cinematic Caption — Audrey, beta: Designed editorial captions for HyperFrames: scored hero words, subject-aware depth, glass type — not a subtitle strip.
• Jump Cut — varg: Cut out a stretch inside one continuous shot, so the subject visibly jumps. Removes pauses, adds pace.
• Jump-Zoom Punch-In — HeyGen: Hide a jump cut by scaling the next segment 110–130%. Reads as a second camera angle in talking heads.

Styles (1)

• Halftone Collage B-roll — pyang5166, beta: Editorial halftone paper-collage B-roll from one line of script, with three approval gates before any video spend.

Guides (2)

• Spoken Script Writer — dlazyai, beta: Writes short-video talking-head scripts in a fixed 7-step story structure for a personal brand
• SmartCut (capcut-ai-editor) — mrbuslov: MCP that reads CapCut auto-captions to cut silences and duplicate takes right inside your CapCut project.

Workflows (14)

• Character Keynote — varg, beta: One render call: a Soul character delivers a keynote-style ad line on a generated stage, voiced by Seedance 2.5.
• Consistent Characters — varg, beta: Multi-scene ads where the same actors, outfits and location hold in every cut: cards, composites, Kling v3 clips.
• Turn a script into a two-person podcast video — varg, beta: Two-character podcast or debate clips: one studio set, locked camera angles, MiniMax H3 Max with native audio.
• fal UGC — fal: Script and generate UGC-style creator ads: talking heads, demos, testimonials, unboxings and reactions.
• Talking Head Production — inference.sh: Produce talking-head videos with AI avatars, lip-sync and voiceover, from portrait specs to final cut.
• AI Podcast Video — inference.sh: Generate a multi-person talking-head podcast video from scratch: characters, voices, avatars, stitching.
• Lanshu AI Presenter Video — Lanshu: Publish-ready explainers led by an AI presenter from an authorized photo, or in one of twelve presenter-free styles.
• Chengfeng Videocut — chengfeng: Chinese talking-head editing: word-level transcript, five-pass flub sweep, human review in a Studio, subtitles, export.
• Herk Edit Kit — Nate Herk: Nate Herk's kit to edit talking-head videos, reels and Shorts: silence and flub cuts, storytelling, motion graphics.
• OpenMontage — Calesthio: Open-source agentic video studio: 12 pipelines (8 edit your footage), 100+ tools, ~140 skills. Run your agent in it.
• video-use — Browser Use: Drop raw takes in a folder, chat with your agent, get final.mp4: transcript-first cuts, grade, subtitles, overlays.
• claude-youtube-editor — Hasan Aboul Hasan: Record a talking head; Claude Code does the cut, Remotion visuals, voice, SFX, thumbnail and YouTube upload.
• ghost-editor — kurbaitaev: Talking-head reel editor in your agent: best takes, face-safe word captions, motion graphics, 7 styles.
• SeeCut — YeJe-cpu: Talking-head and AI-avatar fine cut that watches its own render with Gemini and iterates up to three versions.

Models & tools (6)

• varg AI — varg: The official varg skill: videos, images, speech and music through one API key, rendered in the cloud or locally.
• AI Avatar Video — inference.sh: Create talking-head avatar videos from a portrait and a script, with a lip-synced voice.
• P-Video Avatar — inference.sh: Turn one portrait into a speaking avatar video with Pruna P-Video-Avatar, its built-in TTS or your audio.
• VectCut — sun-guannan, beta: Drives the VectCut editing API: talking-head cuts, remixes, e-commerce ads, subtitles, effects, cloud render
• Jimeng Dream Actor via dLazy — dlazyai, beta: Animate a still character image into an action video with Jimeng Dream Actor, through the dLazy CLI.
• OmniHuman 1.5 via dLazy — dlazyai, beta: Turn a portrait photo and an audio track into a talking digital-human video with OmniHuman 1.5, via the dLazy CLI.