HeyGen Video Translation
Translates an existing video into another language, optionally regenerating the speaker's mouth movements to match the new audio.
- Up to
- 3600 seconds
- Resolution
- 3840x2160
- Weights
- Not released
- API
- Yes
- Commercial use
- Permitted subject to conditions
Offered in a faster Speed mode (audio-only or lip-sync) and a higher-quality Precision mode with lip-sync. Available in the HeyGen app and through the pay-as-you-go API.
Translating a video containing a real person's face and voice engages HeyGen's likeness rules: users must hold rights and consent for the depicted person, and HeyGen removes content where likeness or voice is used without permission.
- Requires consent from the person depicted. Translating a video containing a real person's face and voice engages HeyGen's likeness rules: users must hold rights and consent for the depicted person, and HeyGen removes content where likeness or voice is used without permission
Specification
- What it takes in
- video, audio
- What it makes
- video, audio
- Maximum duration
- 3600 seconds
- Maximum resolution
- 3840x2160
- Controls
- translation, lipsync, voice-clone, auto-captions
- Weights
- Not released
- API
- Yes
- Pricing
- API: Speed mode (audio-only or lip-sync) $0.0333/sec, Precision with lip-sync $0.0667/sec, from a prepaid USD wallet. In-app: 5 credits per minute for translation with lip-sync against plan credit allowances (Creator 600/mo, Pro 1,000/mo, Business 1,500/mo).
- Released or updated
- not established
- Languages
- not established
Strengths
- Two documented quality/price tiers rather than one opaque setting
- Per-second API pricing published
- Same platform as avatar generation, so one integration covers both
Weaknesses
- Number of supported languages not stated on the pages fetched
- Lip-sync fidelity on complex footage not characterised in vendor docs
- Video length ceiling is a plan attribute, not a translation-specific published limit
Best for
- Localising marketing and training video at volume
- Multi-market social campaigns
- Adding dubbing to an existing HeyGen workflow
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.
- Duration and resolution ceilings are inherited from HeyGen plan limits rather than published as translation-specific limits.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
MCP servers that front HeyGen
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
AvatarFactory
The AI influencer MCP for Claude: research trends and write reel scripts, render in the app.
-
Creative Claw
On-brand creative studio for AI agents: images, video, audio, and 3D.
-
Framesail
Create long-form YouTube videos end to end: script, storyboard, voiceover, final MP4.
-
Hermoso
AI ad studio: competitor ad research, video + image ads, social publishing, campaigns. 247 tools.
-
Picsart GenAI
Generate and edit images, videos and audio with 150+ AI models.
-
Prizmad
Generate AI UGC video ads from any product URL, avatars, voiceover, OAuth Connect.
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
Azure AI Speech text-to-speech (Neural, Neural HD, MAI voices)
Microsoft's enterprise speech synthesis service, with 200+ prebuilt neural voices across 80+ locales plus tiers for HD voices, multilingual voices, mu
Voice and speech
Sonic 3.5
Cartesia's current TTS model, documented at sub-90ms first-byte latency across 42 languages. It is tuned for conversational delivery and for reading a
Voice and speech
XTTS-v2
An open-weights multilingual TTS and voice cloning model covering 17 languages at 24kHz, still widely used for local voice cloning. Coqui Inc. shut do
Voice and speech