Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Balance
Subscription
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksEarn crypto
  1. Models
  2. Video

AI Video Translator

Try Model

Translate and dub a talking video into 28 languages while retaining each speaker’s cloned voice and speech timing. Preserve or remove original music and sound effects, and optionally download translated SRT subtitles with a soft subtitle track in the MP4. The original picture, frame rate and resolution stay unchanged. Source videos up to 2 hours.

Added Oct 15, 2026

Details

Starting Price
From $0.425 per video
Model type
video-to-video

Final price depends on the selected settings and is shown before generation.

Settings

Generation controls available for this model.

Output Format

N/A

Default Duration

N/A

Music and sound effects

Select

Default

keep

Options (2)

Keep, Remove

Source language

Select

Default

auto

Options (102)

Detect automatically, English, Chinese (China), Chinese (Taiwan) +98 more

Target must differ from the spoken source. Set the source if automatic detection is unreliable.

Speakers

Select

Default

auto

Options (5)

Detect automatically, 1, 2, 3 +1 more

Target language

Select

Default

en

Options (28)

English, Spanish, French, German +24 more

Translated subtitles

Toggle

Default

No

Download an SRT file and include a soft subtitle track in the MP4.

Translation glossary

Text

Default

N/A

Up to 100 entries, one per line, as source=translation. Example: NanoGPT=NanoGPT.

Benchmarks

No public benchmark scores for this model yet.

Examples

Loading examples…

Related video models

Compare AI Video Translator with similar models from the same provider or model family.

AI Video Captioner

wavespeed-ai/ai-video-editor/video-captioner

Add animated word-by-word captions to a talking video with 12 styles, keyword highlights, emoji, language detection and translation. Optionally remove silence and filler words. Customize typography, colors and placement; download the captioned MP4 plus SRT and VTT subtitles. Processes the first two hours.

OpenJutsu

wavespeed-ai/openjutsu

Swap characters, change objects, or replace the background in a video. Character swap accepts 1–4 images with optional matching descriptions of who to replace; one image without a description replaces the prominent person. Object change uses a target and a description or optional reference image. Background mode keeps the named target and changes its surroundings. Use a single shot; character swaps need a person visible in the first frame. Processes at most the first 15 seconds and aims to retain motion and original audio; results can be shorter. Choose 480p or 768p and an optional seed.

Video Music Remover

wavespeed-ai/video-music-remover

Remove background music from a video while preserving dialogue, sound effects, and the picture. Videos longer than 10 minutes are trimmed to the first 10 minutes; clips without audio are returned unchanged.

InfiniteTalk

wavespeed-ai/infinitetalk

Animate one or two people from an image and audio tracks.

MiniMax H3 Spicy Image-to-Video

wavespeed-ai/minimax-h3/image-to-video-spicy

Open-weights MiniMax H3 image-to-video generation with expressive unrestricted motion, native stereo audio, optional last-frame control, 3–15 second clips, and 480p or 768p output.

LTX-2.3 Spicy Image-to-Video

wavespeed-ai/ltx-2.3-spicy/image-to-video

LTX-2.3 Spicy image-to-video turns a reference image and prompt into expressive clips with native audio, style-tuned motion, 480p/720p/1080p output, and 3-20 second durations.