tavus-replica-video
Use for producing Tavus AI-human videos and real-time avatar conversations with Tavus Faces/Replicas, PALs/Personas, async Video Generation, CVI conversations, consent-safe likeness workflows, webhooks, backgrounds, localization, and avatar QA.
Profile →npx skills add calesthio/generative-media-skills --skill tavus-replica-video --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Instructs an agent to handle Tavus avatar and video tasks, including real-time avatar conversations, async video generation, consent safeguards, backgrounds, localization, and avatar QA. Focuses on producing Tavus AI-human videos and real-time avatar conversations using Tavus Faces/Replicas, PALs/Personas, and related features.
How it works
- Explains Tavus object model: Face (on-screen likeness/voice), PAL (behavior/pipeline/config for CVI), and Conversation (real-time video with PAL and face).
- Guides choosing the Tavus path by deliverable: one-way talking-head file via async Video Generation; interactive AI human via CVI; new likeness via Face creation; exact audio via audio_url or CVI echo mode; lip-sync via LipSync path with caveats.
- Enforces consent requirements before uploading likeness or biometric material, listing explicit consent scope and disallowing certain use cases.
- Details Face creation workflows (Video-to-Face and Image-to-Face) with API endpoints, required fields, and training considerations.
- Describes Async Video Generation: endpoint POST https://tavusapi.com/v2/videos, required replica_id and either script or audio_url, with optional background and delivery fields, and status lifecycle (queued/generating/ready/etc.).
- Covers CVI / PAL conversations: endpoints for PAL creation (POST /v2/pals) and conversations (POST /v2/conversations), required fields like default_face_id and system_prompt, and modes (full vs echo).
- Provides webhook and lifecycle guidance: how to log payloads, poll status, callbacks, and archival rules for video and training artifacts.
- Includes QA and identity/consent checks, voice/performance notes, framing/background considerations, and CVI-specific guardrails.
When to use it
Use this skill when tasks involve Tavus avatars, replicas, or faces, including generated talking-head videos, real-time avatar conversations, or Tavus-enabled lip-sync and QA workflows. It also applies when consent, localization, backgrounds, and governance are required for Tavus-produced media.
What it can touch
- API endpoints cited: POST /v2/videos, POST /v2/faces, POST https://tavusapi.com/v2/faces, POST /v2/pals, POST /v2/conversations.
- Data fields include replica_id, face_id, script, audio_url, video_name, background_url, callback_url, system_prompt, default_face_id, and various conversation and guardrail parameters.
- No explicit scripts or external tools beyond the Tavus API references are listed in this skill.
Caveats
- Documented facts are verified as of 2026-07-10 and may change; verify API names, model names, plan limits, and policy wording before committing spend or production use.
- Some workflows may require current OpenAPI contracts for lip-sync path caveats; confirm endpoint availability before promising a path.
- Consent requirements are strict: explicit informed consent is mandatory for each type of biometric material and usage scope.
- Output discusses background URLs, signed URLs, and custody rules; ensure asset custody compliance in production.
# Tavus replica video production Use this skill when a task involves Tavus avatars, replicas, faces, PALs/personas, generated talking-head files, real-time conversational video agents, or Tavus-powered lip-synced presenter output. Documented facts in this skill were checked against official Tavus docs, policies, and pricing on 2026-07-10. Treat API names, model names, plan limits, stock replica av
What does the tavus-replica-video skill do?
Use for producing Tavus AI-human videos and real-time avatar conversations with Tavus Faces/Replicas, PALs/Personas, async Video Generation, CVI conversations, consent-safe likeness workflows, webhooks, backgrounds, localization, and avatar QA.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill tavus-replica-video --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.