Clone a voice and create talking avatar videos using Anthropic and deAPI
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 10 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Anthropic Chat Model and Deapi (community).
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Set Fields (Edit Fields (Set)): sets 3 fields: text, video_prompt, lang
- Read Reference Audio (Read/Write Files from Disk): reads a file from disk
- Read First Frame Image (Read/Write Files from Disk): reads a file from disk
- Deapi: work with audio
- Merge: merges the data from its input branches
- AI Agent: runs an AI agent, with model: Anthropic Chat Model; 1 tool (Video prompt booster in deAPI)
- Deapi: generate from audio (video)
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (8)
- Manual Trigger
n8n-nodes-base.manualTrigger - Edit Fields (Set)
n8n-nodes-base.set - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - Deapi
n8n-nodes-deapi.deapi - AI Agent
@n8n/n8n-nodes-langchain.agent - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - Deapi Tool
n8n-nodes-deapi.deapiTool - Merge
n8n-nodes-base.merge
From the author
Who is this for? - Content creators who want a consistent on-screen avatar without filming themselves - Marketing teams producing personalized video messages at scale - Educators building video lessons with a virtual presenter - Anyone who wants to turn text…