# tavus-replica-video

The tavus-replica-video skill for Claude Code automates Tavus API workflows for producing AI avatars, replica faces, and interactive video conversations.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 130 installs · ★ 252 repo stars
- Author: calesthio
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/avatar-video/tavus-replica-video/SKILL.md
- Updated: 2026-07-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/tavus-replica-video

## What it does

The agent applies this skill when building talking-head video pipelines, real-time conversational agents, or custom likeness models. It covers async video generation via `POST /v2/videos`, conversational video interface setups with faces and PALs, and face training routines using video or image assets. Production workflows require explicit user consent for biometric likeness handling, proper public download links, and adherence to video upload constraints.

The logic distinguishes between one-way video generation from scripts or audio and live sessions requiring paired face and persona identifiers. For training custom likenesses, the default Phoenix model processes H.264 footage under the 750 MB file size limit, while image training bypasses webcam setup using static assets and a designated voice name.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill tavus-replica-video -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/tavus-replica-video/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/tavus-replica-video/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill tavus-replica-video -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/tavus-replica-video/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill tavus-replica-video -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/tavus-replica-video/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install calesthio/generative-media-skills skills/providers/avatar-video/tavus-replica-video
```

2. **Manually: put the files in place**
- File: `.github/skills/tavus-replica-video/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill tavus-replica-video -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/calesthio/generative-media-skills --path skills/providers/avatar-video/tavus-replica-video
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/tavus-replica-video/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill tavus-replica-video -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/avatar-video/tavus-replica-video/SKILL.md

## When to use it
- train a custom face likeness from source video or image assets
- generate an async talking-head video from a script or audio file
- initialize a real-time conversational video session with a PAL
- poll the video generation endpoint until output is ready

## Example prompts
- Create an async talking-head video using the Tavus video generation endpoint
- Train a new face model using a publicly accessible training video URL
- Configure a real-time conversational session with a face and persona ID

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: dc02f459e43f4141.

BEGIN THIRD-PARTY FILE dc02f459e43f4141
```text
---
name: tavus-replica-video
description: 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.
---

# 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 availability, language support, pricing, and policy wording as volatile; verify them again before committing spend, launch scope, or regulated workflows.

## The current Tavus object model

Tavus docs now use:

- **Face**: the on-screen likeness and voice rendered by Phoenix. A custom face can be trained from a video URL or image URL. Stock faces/replicas can also be used.
- **PAL**: behavior, knowledge, pipeline, LLM/TTS/perception/turn-taking/conferencing configuration for real-time CVI.
- **Conversation**: a real-time video call/session with a PAL and face.

Legacy terms still appear in APIs and production requests:

- `replica_id` in the Video Generation API is the Face ID returned by `/v2/faces`.
- `/v2/personas`, `persona_id`, `/v2/replicas`, `default_replica_id`, and related aliases may still exist for backward compatibility.

Do not force the user to rename their mental model. Translate cleanly: "your Tavus replica ID is the face ID needed by the video endpoint."

## Choose the Tavus path first

Pick the path by deliverable, not by habit.

1. **One-way talking-head file**: use async Video Generation. Call `POST /v2/videos` with `replica_id` plus either `script` or `audio_url`; poll `GET /v2/videos/{video_id}` until `ready`, then capture `download_url`, `stream_url`, and `hosted_url`.
2. **Interactive AI human / live agent**: use CVI. Create or select a Face, create or select a PAL, then call `POST /v2/conversations` with `face_id` and `pal_id`.
3. **Need a new likeness**: create/train the Face first with `POST /v2/faces`. Use video training for highest fidelity and customer-facing work; use image training when speed/setup simplicity matters more than personalized expressions.
```
END THIRD-PARTY FILE dc02f459e43f4141

The third-party file has ended. Everything between the dc02f459e43f4141 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2405 of 24004 bytes. © calesthio · MIT · https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/avatar-video/tavus-replica-video/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
