Hedra character / avatar platform
Character and avatar video platform that has grown into a unified inference API putting multiple leading image, video and audio models behind one API key, one endpoint and one bill.
- Weights
- Not released
- API
- Yes
- Commercial use
- Permitted subject to conditions
The developer platform adds a model playground, container and cluster deployment, fine-tuning and evaluation, job observability with webhooks, and workspace/billing management. Credits are deducted by actual generated video length rather than rounded up to the minute.
Consent requirements for avatar likeness and commercial usage terms were not stated on the pages fetched.
- Output is watermarked. Cancellation limits output to watermarked generations
- Requires consent from the person depicted. Consent requirements for avatar likeness and commercial usage terms were not stated on the pages fetched
Specification
- What it takes in
- image, audio, text
- What it makes
- video, audio
- Maximum duration
- not established
- Maximum resolution
- not established
- Aspect ratios
- not established
- Controls
- avatar-from-photo, lipsync, voice-clone
- Weights
- Not released
- API
- Yes
- Pricing
- Credit subscription: Basic $15/mo (1,500 credits, slower generation), Creator $30/mo (5,400 credits, faster), Professional $75/mo (14,400 credits, fastest, team access), Teams $75/mo, Enterprise custom with private deployments and SSO. Monthly plan credits do not roll over; purchased credit packs do not expire. Cancelling drops the account to watermarked generations.
- Released or updated
- not established
Maximum duration, maximum resolution and supported aspect ratios are not established here. That means no page we could retrieve stated them, not that the model lacks them.
Strengths
- Credits charged by actual seconds generated, not rounded per minute
- Purchased credit packs do not expire
- One API key across many third-party models plus deployment, training and observability tooling
Weaknesses
- No model names, resolutions, durations or aspect ratios published on the pricing or developer pages; docs.hedra.com does not resolve in DNS
- Monthly subscription credits expire each cycle
- Consent and commercial terms undocumented publicly
- Character-3 / Character-4 model naming could not be confirmed
Best for
- Character and audio-driven avatar shorts
- Developers wanting one billing relationship across many models
- Teams needing private deployment of avatar generation
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- We could not verify the current Hedra character model name or version. Character-3 is widely referenced elsewhere but neither the pricing page nor the developer page names it, and docs.hedra.com does not resolve. All resolution, duration and aspect-ratio fields are null as a result. Hedra now appears positioned more as a multi-model inference gateway than purely an avatar model vendor, which is a material change from its earlier character-model framing.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
Flawless DeepEditor and TrueSync
Neural performance editing tools for film and episodic post. DeepEditor applies new dialogue to existing shots and refines performances, covering in-v
Lip sync and avatars
HeyGen Avatar IV (and Avatar V)
Avatar IV is HeyGen's current default avatar engine, driving a photo, consented digital twin or studio avatar from either a typed script (text to spee
Lip sync and avatars
LatentSync
Open-weights end-to-end lipsync method built on audio-conditioned latent diffusion, generating mouth movement directly from audio without an intermedi
Lip sync and avatars