Skip to main content

​
Overview

Enterprise plans work the same way as self-serve — the difference is the unit. Where self-serve bills in USD, Enterprise plans are billed in credits, and 1 credit costs $0.50. To map an enterprise rate to the self-serve page, multiply the credit rate by $0.50: for example, Photo Avatar video at 0.1 credits / sec is the equivalent of $0.05 / sec.

​
Pricing

​
Video Generation — Avatar V

Highest-fidelity engine with cross-reference-driven animation — see the Avatar V model page for engine details. Avatar V supports Digital Twins only.

​
Video Generation — Avatar IV

Default v3 engine — see the Avatar IV model page for engine details.

​
Video Generation — Avatar III

Dedicated photo-to-video pipeline — see the Avatar III model page for engine details.

​
Video Generation — Avatar III (Legacy v1/v2)

This is the older Avatar III engine on the legacy v1/v2 endpoints — a different pipeline from the avatar_iii engine above. It is available to existing customers only and is not offered on the new developer platform. For all new integrations use the v3 engines: Avatar IV, Avatar V, or Avatar III.

​
Cinematic Avatar

Flat rate per video (4–15 seconds, 720p/1080p only), not billed by duration. See the Cinematic Avatar guide.

​
Video Agent

​
HyperFrames

Billed per minute of output video; the rate scales with resolution and fps. See the HyperFrames guide.

​
Video Translation

​
Lipsync

​
AI Clipping

Turn a long-form video into short highlight clips, billed per clip produced. See the AI Clipping guide.

​
Filler Word Removal

Cut filler words and overlong silences out of a finished recording, billed on the source video’s duration with a 1-minute minimum per job. If a run changes nothing, the charge is automatically refunded. See the Filler word removal guide.

​
Text-to-Speech

​
Avatar Creation

​
Concurrency Limits

Concurrent jobs include any asynchronous generation in progress: Video Agent sessions, avatar video renders, and video translations. Exceeding the limit returns 429 Too Many Requests with a Retry-After header.

​
Endpoint Limits

​
Video Generation Input

Resources provided to POST /v3/videos must meet these limits. Invalid resources will cause render failures. Requirements:
  • Resource URLs must be publicly accessible (no authentication required).
  • The file extension must match the actual file format.
  • Files must not be corrupted or malformed.

​
Avatar Input

  • Script text: Maximum 5,000 characters.
  • Audio input: Maximum 10 minutes (600 seconds).

​
Video Agent Input

  • Prompt: 1–10,000 characters.
  • File attachments: Up to 20 files. Supported types: image (PNG, JPEG), video (MP4, WebM), audio (MP3, WAV), and PDF.
  • Files can be provided as an asset_id (from POST /v3/assets), an HTTPS URL, or base64-encoded content.

​
Asset Upload (POST /v3/assets)

  • Maximum file size: 32 MB. The same limit applies to files provided by URL. For larger files, use the direct upload flow (POST /v3/assets/direct-uploads).
  • Supported types: Image (PNG, JPEG), video (MP4, WebM), audio (MP3, WAV), and PDF.

​
Text-to-Speech Input (POST /v3/voices/speech)

  • Text length: 1–5,000 characters.
  • Speed multiplier: 0.5× to 2.0×.
  • Input type: Plain text, with <break time="1s"/> pause tags supported for pacing.

​
Output Video Specifications

  • Frame rate: 25 fps for videos containing avatars.
  • Resolution: Width and height must each be between 128 and 4,096 pixels. Default output is 1080p (up to 4K on Enterprise).
  • Aspect ratio: 16:9 or 9:16.
  • Maximum scenes: 50 per video.
  • Maximum duration: Custom (contact your account team).

​
Pagination

Most list endpoints use cursor-based pagination with a limit parameter and next_token for the next page.

​
Rate Limiting

All endpoints enforce rate limits. When exceeded, the API returns 429 Too Many Requests with a Retry-After header indicating the number of seconds to wait before retrying.