veed-ugcGenerate UGC-style promotional videos with AI lip-sync. Takes an image (person with product from Morpheus/Ad-Ready) and a script (pure dialogue), creates a video of the person speaking. Uses ElevenLabs for voice synthesis.
Install via ClawdBot CLI:
clawdbot install pauldelavallaz/veed-ugcGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://api.comfydeploy.com/api/run/deployment/queue`Audited Apr 16, 2026 · audit v1.0
Generated Mar 6, 2026
Online retailers can generate authentic user testimonial videos for product pages by using images from ad-ready photoshoots and scripts based on customer reviews. This creates scalable, personalized promotional content that boosts conversion rates without expensive video production.
Marketing agencies can produce high volumes of UGC-style video ads for platforms like Instagram and TikTok by scripting casual dialogue and animating influencer or model images. This enables rapid A/B testing of messaging and visuals to optimize engagement.
Small businesses such as restaurants or salons can create promotional videos featuring staff or customers by using photos from events and scripts in local dialects. This builds community trust and enhances digital presence with minimal technical expertise.
Edtech companies can animate instructor avatars or stock photos with lip-synced explanations from lesson scripts. This makes online courses more engaging and accessible, allowing for quick updates to content without reshooting videos.
Enterprises can develop training videos by using employee photos and scripted dialogues for scenarios like compliance or onboarding. This personalizes learning materials and reduces production costs compared to traditional video filming.
Offer a platform where users upload images and scripts to generate videos via API, with tiered pricing based on video length or volume. This provides recurring revenue from businesses needing regular content updates, such as marketing teams or agencies.
Provide free basic video generation with watermarks or limited features, then charge for high-resolution outputs, faster processing, or custom voice options. This attracts small creators and upsells to professionals requiring premium quality.
License the technology to agencies or platforms that integrate it into their own services, charging per API call or through revenue-sharing agreements. This scales adoption without direct marketing and leverages partners' existing customer bases.
💬 Integration Tip
Ensure scripts are pure dialogue without annotations, and use high-quality frontal face images for best lip-sync results; integrate with image generation tools like Morpheus for a seamless workflow.
Scored Apr 16, 2026
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Local text-to-speech via sherpa-onnx (offline, no cloud)
Speak responses aloud on macOS using the built-in `say` command when user input indicates Voice Wake/voice recognition (for example, messages starting with "User talked via voice recognition on <device>").
Transcribe audio files to text using local Whisper (Docker). Use when receiving voice messages, audio files (.mp3, .m4a, .ogg, .wav, .webm), or when asked to transcribe audio content.