Overview
Video Podcast Generator - 1080p GPU AI Lip Sync with Support
GPU AI video generator producing 1920x1080 lip-synced talking head videos from scripts. SadTalker face animation + Real-ESRGAN 4x upscale. Amazon Polly TTS. No external APIs.
Pre-configured AMI with Docker and GPU container. Auto-starts on boot. Published by Waltsoft.
PIPELINE: Script > Polly TTS > SadTalker (256px) > Real-ESRGAN 4x (1024px) > FFmpeg 1920x1080 @30fps.
PREREQUISITES: GPU instances (g4dn.xlarge or g5.xlarge). EC2 G/VT quota required.
IAM: Attach role with polly:SynthesizeSpeech. Polly ~$4/1M chars billed separately.
USAGE:
- Launch on g4dn.xlarge
- Restrict port 8080 to your IP
- Open http://INSTANCE_IP:8080
- Upload headshots + script
- Generate - 1080p video in 1-2 min/segment
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
- Real-ESRGAN 4x super-resolution produces broadcast-quality face detail
- Zero external API dependencies - all inference runs locally on GPU
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Free trial
Dimension | Description | Cost/hour |
|---|---|---|
g4dn.xlarge Recommended | g4dn.xlarge hourly | $0.10 |
t3.micro | t3.micro instance | $0.00 |
g5.xlarge | g5.xlarge hourly | $0.15 |
t3.xlarge | t3.xlarge hourly | $0.05 |
m5.xlarge | m5.xlarge hourly | $0.05 |
p3.2xlarge | p3.2xlarge hourly | $0.25 |
Vendor refund policy
No refunds. Cancel anytime via AWS Marketplace. Support: support@waltsoft.net
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Major upgrade: SadTalker + Real-ESRGAN replaces Wav2Lip. Output now 1920x1080 @30fps. Amazon Polly TTS (no edge-tts). Zero external API dependencies.
Additional details
Usage instructions
- Launch on GPU instance (g4dn.xlarge or g5.xlarge required)
- Attach IAM role with polly:SynthesizeSpeech permission
- Restrict Security Group port 8080 to your IP only
- Open http://INSTANCE_IP:8080
- Upload speaker headshot images
- Enter script (SPEAKER: text format)
- Click Generate - 1080p lip-synced video in 1-2 min per 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


