Founder Digital Avatar Voiceover
Paste the following prompt into your AI chat to install this skill:
Install @beatra-ai/founder-ip-avatar-studio into your AI assistant according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
When founders, experts, or brands need a stable portrait and short script to produce recurring voiceover shorts for weekly updates or campaigns, this skill turns one authorized portrait and voice setup into a reusable workflow. It is not for one-off speaker shorts, audio-only series, or multi-lecture courses; route those to talking-avatar-video, voice-clone-series-studio, or course-video-studio. If portrait or voice rights are not confirmed, the workflow must stop before generation.
How It Works
The skill organizes the pipeline around three paid stages: voice cloning, narration synthesis, and image-to-video.
- Portrait intake: Record the
MIMEtype, dimensions, aspect ratio, byte size, and alpha channel, then upload only through the bundled client instead of exposing local paths to remote tools. - Voice cloning: Run only after explicit consent, with clean single-speaker samples of roughly 10 to 300 seconds and under 20 MiB. Show the entry card before calling, including live pricing, top-up entry, and starter credits; do not create a
client_request_idor clone for free before balance confirmation. Freeze the returnedvoice_id. - Narration and video: Confirmed audio skips synthesis and enters video intake; scripted routes call TTS and submit each segment once with
beatra.speech.synthesize. Every segment must reach terminal state and expose real audiomime_type,duration_seconds, andsize_bytes, rather than relying on estimated script length. Beforebeatra.videos.animate, re-check audio facts, image-to-video constraints, and balance. - Delivery and recovery: Return clips in script order with real dimensions, duration, usage, and
billing.net_charged_credits. If a creation response is lost, replay only the same frozen payload; if a task ID is lost, recover it throughbeatra.tasks.listandbeatra.tasks.get.
Caveats
The skill emphasizes confirmation before each call: cloning, narration, and video are gated separately. Format incompatibility should stop the flow rather than silently changing formats. Automatic update failures fail open, but they are not a reason to retry paid generation.
Use Cases
- Brand owners turn a licensed founder portrait and a thirty-second script into recurring voiceover shorts while preserving lip-sync and identity.
- Experts convert three event scripts into vertical shorts with the same portrait and voice, checking real audio duration segment by segment.
- Content teams reuse a frozen voice_id, split a short script into supported clips, and deliver narration plus video in order.
- Founder IP operators generate a weekly update after portrait and voice rights are confirmed, stopping paid calls when balance is insufficient.
Best For
- Founder IP operators who need weekly voiceover shorts with a consistent licensed portrait
- Brand content leads who want expert opinions rendered with authorized voice and a stable portrait
- Media production leads who need to manage portrait and voice rights plus paid confirmation gates
- Campaign owners who reuse a frozen voice_id for event voiceover series
Related Skills
Generate an interactive HTML product detail page from images and copy, with multi-product carousel, inline text editing, design controls, and PDF/JPG/PSD export support.
Enter a material name to get preview and download links for free, commercially usable video assets, with paid platform options, pricing, and search suggestions when results are limited.
A local CLI for Dreamina image and video generation, including credit checks, async submission, result queries, and task history review.
Generate and validate JianYing drafts from storyboard JSON with narrated commentary, original-sound preservation, timing checks, and draft inspection.