Sold by: Waltsoft Inc.
Deployed on AWS
Containerized GPU video generator producing 1920x1080 lip-synced talking head videos from a single photo and audio input.
Overview
Video Podcast Generator Container - 1080p GPU Lip Sync with Support
Containerized GPU video generator producing 1920x1080 lip-synced talking head videos. SadTalker + Real-ESRGAN 4x upscale. Pre-baked models, deploy on any GPU instance.
Docker image with all models pre-loaded (14GB). Deploy with nvidia-container-toolkit. Published by Waltsoft.
PIPELINE: Script > Polly TTS > SadTalker > Real-ESRGAN 4x > FFmpeg 1920x1080 @30fps.
DEPLOYMENT: docker run --gpus all -p 8080:8080
Web UI on port 8080 + REST API (POST /generate, GET /status/, GET /download/).
PREREQUISITES: GPU instance with nvidia-container-toolkit. IAM role with polly:SynthesizeSpeech.
SECURITY: This AMI binds services to localhost only. Configure a reverse proxy (Nginx/Caddy) with HTTPS for production access. Change all default passwords immediately after launch.
IMPORTANT: This product requires a GPU instance (g4dn.xlarge or g5.xlarge minimum). It will not function on CPU-only instances (t3, m5, etc.) as neural face animation requires NVIDIA CUDA. Performance varies by GPU type. Waltsoft provides the pre-configured deployment only and does not guarantee upstream software functionality.
Highlights
- 1920x1080 @30fps output with neural lip sync from single headshot photo
- Self-contained Docker image with all models pre-loaded, no runtime downloads
- Web UI plus REST API for programmatic integration and automation
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
ECS GPU Container
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/hour |
|---|---|---|
Video Podcast Generator | Hourly software fee | $0.10 |
Vendor refund policy
No refunds. Cancel anytime via AWS Marketplace. Support: support@waltsoft.net
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
ECS GPU Container
Supported services: Learn more
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
SadTalker + Real-ESRGAN. 1920x1080 @30fps. Amazon Polly TTS. No external APIs.
Additional details
Usage instructions
CONTAINER IMAGE URI: 709825985650.dkr.ecr.us-east-1.amazonaws.com/waltsoft/waltsoft/vpg-paid:v4
ECS TASK DEFINITION:
- Family: video-podcast-gpu
- CPU: 4096, Memory: 16384 MB, GPU: 1 (NVIDIA T4)
- Network Mode: awsvpc, Port: 8080
- Placement: g4dn.xlarge or g5.xlarge
- Task Role: aws-marketplace:RegisterUsage + polly:SynthesizeSpeech
- Env: AWS_MARKETPLACE_PRODUCT_CODE=14gf4p7nh2r5dk72tyuzxqz2w
NETWORKING:
- awsvpc mode, assign public IP
- Security Group: inbound TCP 8080
- Internet access for AWS Polly
OUTPUT:
- Web UI: http://TASK_IP:8080
- Upload headshot + text -> 1080p MP4 with lip sync
- Startup: ~60s, Processing: 1-2 min/segment
Support
Vendor support
Email: support@waltsoft.com | Response within 24 hours.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
GPU AI video generator producing 1920x1080 lip-synced talking head videos from scripts. SadTalker face animation + Real-ESRGAN 4x upscale. Amazon Polly TTS. No
Callaba runs live video workflow infrastructure in your AWS account. Receive SRT and RTMP feeds, monitor sources in browser multiview, switch between main and backup streams, route video to outputs, record live events, convert SRT to NDI, and automate workflows through API.
Secure, Simple and Scalable Video Conferences. A Zoom alternative, Jitsi Meet is an open-source (Apache) WebRTC JavaScript application that uses Jitsi Videobridge to provide high quality, secure and scalable video conferences.
The Fortinet FortiRecorder-VM is the core of a network video surveillance solution offering secure access to live and recorded camera streams from anywhere there is an Internet connection.
View it on mobile devices or work with the sophisticated FortiRecorder Central Video Management System.
DeepField-SR is a fixed functional hardware accelerator leveraging FPGA to offer the highest computational efficiency for Video Super Resolution.
The AMD Xilinx Video SDK is a complete software stack allowing users to seamlessly leverage the hardware accelerated features of AMD Xilinx video codecs such as the ones available on Amazon EC2 VT1 instances.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.