Move from stock avatars and ad templates to full production
Vidnoz sells minutes of stock-avatar video and Topview turns product links into UGC-style ads. Hedra Agent and Workspaces produce the whole piece with your own presenter, footage and voice, on avatar and video models served on GPU infrastructure Hedra runs itself.
export HEDRA_API_KEY="<key_id>:<secret>"
curl -X POST \
"https://api.hedra.com/v3/models/kling-ai-avatar-v2" \
-H "Authorization: Key $HEDRA_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "input": {
"prompt": "A presenter speaks to camera in a bright kitchen",
"aspect_ratio": "16:9",
"start_image": "https://example.com/presenter.png",
"audio": "https://example.com/script.mp3",
"quality": "pro"
} }'A more modern way to work
Skip the model aggregators. Hedra Agent and Workspaces give your team an autonomous agent that supercharges your workflows with a superintelligent understanding of the latest models: brief it in a shared space and it plans, generates, and edits across video, image, speech, and music, with your team and your agents working alongside it.
GPU infrastructure, an inference engine, and post-training research
Hedra operates GPU clusters and the inference engine that runs diffusion and autoregressive media models on them 8x faster. The same research team post-trains models for customers: supervised fine-tuning, LoRA training, and GRPO, on your data.
Hedra, Vidnoz and Topview: focus at a glance
Vidnoz and Topview are template products over other companies' models. Hedra is the infrastructure those models run on, and the agent that replaces the template.
| Dimension | Hedra | Vidnoz and Topview |
|---|---|---|
| What it is | GPU infrastructure, inference and post-training research | Vidnoz: freemium stock-avatar video by the minute. Topview: product links into UGC-style ads |
| Core technology | Hedra's inference engine, its own GPU clusters, and post-training (SFT, LoRA, GRPO) | Avatar libraries and ad templates over third-party models |
| Models | Open-weight models on Hedra's engine, models post-trained for you, and partner models through a gateway | Third-party models behind their templates |
| How you connect | API, SDK, CLI, MCP, and Hedra Workspaces | Vidnoz app: free 3 minutes a day with a watermark, Starter $26.99 and Business $74.99 a month. Topview app from $18 a month. As of September 2026 |
| Where inference runs | Hedra's GPU clusters, or your own | Their clouds and their model providers |
| Best fit | Teams building visual products who need inference, capacity and custom models | Solo marketers making quick avatar explainers and product ads |
Avatar, video and voice models on Hedra infrastructure
Video rates are per second of generated performance or clip; voice rates are per 1,000 characters. Partner models are reached through the gateway; open weights run on Hedra's engine.
| Provider | Model ID | Rate |
|---|---|---|
| ByteDance | omnihuman-15 | 16¢/s · 1080p |
| Kling | kling-ai-avatar-v2 | 11.5¢/s · 720p pro |
| HeyGen | heygen-photo-avatar-4 | 10¢/s · up to 1080p |
| Creatify | creatify-aurora | 14¢/s · 720p |
| Kling | kling-v3 | 16.8¢/s · 1080p |
| ElevenLabs | elevenlabs-v3 | 12.6¢ / 1,000 characters |
| MiniMax | minimax-speech-25-hd-preview | 12.86¢ / 1,000 characters |
FAQs
- Can Hedra make avatar videos like Vidnoz?
- Yes, from your own presenter. Avatar models on Hedra animate a reference image with an audio track, and voice models from ElevenLabs and MiniMax cover the narration. There is no minutes plan; you pay per second of generated video at the rates above.
- Can Hedra make product ads like Topview?
- Yes. In Hedra Workspaces the agent takes a brief, a product image or a URL, and plans, generates and edits the ad across image, video and voice models. Developers get the same models through the API and MCP server.
- What does Hedra actually operate?
- GPU clusters, the inference engine that serves media models on them, and a research team that pre-trains and post-trains models. Open-weight models and models post-trained for customers run on that engine, on Hedra's clusters or inside your perimeter. Partner models that only their makers serve are reached through Hedra's gateway so one request shape covers both.
