Repurpose viral TikToks into AI avatar videos across 9 platforms

See What's Earning in AI Automation Freelancing.
DigiNo helps new AI automation freelancers earn faster by tracking what clients actually pay for.

Personal brands and course creators need a constant stream of short-form video across every platform, but manually rewriting, filming, and uploading content kills hours every week. This AI automation handles the entire pipeline from a single TikTok URL to a published, branded video on nine platforms.

What This Automation Does

Downloads a TikTok video and extracts its audio, thumbnail, and caption, then transcribes and stores the original content in Google Sheets for reference
Uses Perplexity AI to identify a fresh content angle in the same niche, then rewrites the script, caption, and on-screen overlay text with GPT-4o to match the client's voice
Generates a new video featuring the client's AI avatar via Captions.ai and adds branded subtitles and overlay text through JSON2Video
Auto-publishes the finished video to Instagram, YouTube, TikTok, Facebook, LinkedIn, Threads, X, Pinterest, and Bluesky through Blotato in a single automated push

Tools Used

n8n
OpenAI
Telegram
Google Sheets
Perplexity

Where to Get Hired for This Skill

On Contra, top freelancers across this stack have earned 156 combined verified reviews from real client projects.

Source: Contra freelancer search · refreshed 26 May 2026

Start Earning as a Freelancer on Contra

Contra is a commission-free professional network for independents. Browse live AI automation work and keep what you earn.

Join Contra Free →

How To Build It

Wire Telegram as the intake trigger

The workflow starts when a TikTok URL is sent to a Telegram bot, so the client's only job is dropping a link into a chat, making the entire process hands-off from the first second.

Extract and transcribe the source video

The workflow downloads the TikTok video, pulls the audio track, thumbnail, and existing caption, then transcribes the spoken content and logs everything into a Google Sheet so the client has a permanent record of every source asset.

Generate a rewritten script with Perplexity and GPT-4o

Perplexity AI analyses the niche and surfaces a relevant content angle, then GPT-4o rewrites the full script, caption, and overlay text to reflect the client's tone and branding rather than cloning the original creator's style verbatim.

Build a branded AI avatar video with overlays

The rewritten script is sent to Captions.ai to produce a new video using the client's AI avatar, then JSON2Video adds synced subtitles and styled overlay text before the final file is delivered to Telegram for the client to preview and approve.

Publish to nine platforms via Blotato

Once the video passes review, Blotato distributes it simultaneously to Instagram, YouTube, TikTok, Facebook, LinkedIn, Threads, X, Pinterest, and Bluesky using pre-configured account IDs, with all publishing metadata saved back to Google Sheets for tracking.

Pitfalls

Avatar voice drift is a real problem at scale: Captions.ai avatar outputs can sound inconsistent across batches if the source audio quality varies, so always pre-process audio to a consistent sample rate and volume before sending it to the avatar generation step.
Blotato platform tokens for Instagram, TikTok, and LinkedIn expire on their own schedules, and a single expired credential silently fails the publish step for that platform without erroring the whole workflow, so build a post-publish check in Google Sheets that flags any platform that did not receive a confirmed post ID.
Perplexity API rate limits can stall the workflow during high-volume runs, and because the script rewrite depends on Perplexity completing before GPT-4o continues, a timeout here blocks the entire downstream chain, so add a wait-and-retry buffer between the Perplexity call and the GPT-4o rewrite step.

FAQ

Can I build this without coding?

The majority of this workflow is configuration rather than code. You will need to write a small amount of JSON to format API payloads for JSON2Video and to map platform IDs in the publishing step, but nothing requires a programming background. Familiarity with reading API documentation is more important than coding skill.

How long does it take to build?

Expect six to ten hours for a first build, spread across connecting five separate API services, configuring the Google Sheet schema, and testing the end-to-end run with a live TikTok URL. A second build for a new client typically takes two to three hours once you have a working template.

What can I charge for this service?

Pricing is your decision based on your market and positioning. A common packaging approach is to offer a fixed number of AI avatar videos per week delivered across all nine platforms as a monthly retainer, which shifts the conversation away from hourly rate and toward predictable output volume for the client.

Which tools are required versus optional?

Telegram, OpenAI, Captions.ai, and Blotato are load-bearing: removing any of them breaks the core loop. Perplexity can be swapped for a second GPT-4o call if a client does not want another API account. JSON2Video handles subtitle and overlay styling and can be replaced with a different video API if you already have a preferred provider.

This is original DigiNo analysis. The underlying automation pattern is a community workflow template – view the original on n8n.