xAIVideo
Grok Imagine
Create a short video shot from a supported prompt or reference image, then combine it with your own footage. Subclip is a separate product from the Grok app.
Compare versionsExplore every image, video, audio, avatar and speech model available in Subclip.
64 / 64
2.125 credits/sec - 720p
Animate a portrait using a supplied speech recording.
4.25 credits/sec - 720p
Animate one portrait using supplied speech. The prompt describes motion, not the spoken script.
13.6 credits/sec
Animate a portrait using a supplied speech recording.
4.76 credits/sec
Animate a portrait using a supplied speech recording.
1.19 credits/sec
Synchronize an existing video with supplied speech.
4.25 credits/1K characters
Speech synthesis with model-specific voices and delivery controls.
2.125 credits/1K characters
Speech synthesis with model-specific voices and delivery controls.
4.25 credits/1K characters
Speech synthesis with model-specific voices and delivery controls.
8.5 credits/1K characters
Speech synthesis with model-specific voices and delivery controls.
5.1 credits/1K characters
Speech synthesis with model-specific voices and delivery controls.
4 credits/generation - medium
Create media with model-specific quality and reference controls.
4 credits/generation - medium
Create media with model-specific quality and reference controls.
6 credits/generation - Medium
Precise instruction following, typography, photorealism, and editing.
2.5 credits/generation - 1K
Fast, versatile generation and conversational image editing.
2.86 credits/generation - 1K
Create media with model-specific quality and reference controls.
2.89 credits/generation
Create media with model-specific quality and reference controls.
6 credits/generation - 1K
Reasoning-heavy image generation with accurate multilingual text.
2.04 credits/generation - 1k
Create media with model-specific quality and reference controls.
2.55 credits/generation - 1 MP
Create media with model-specific quality and reference controls.
3.4 credits/generation - 2k
Create media with model-specific quality and reference controls.
2.98 credits/generation - 2K
Create media with model-specific quality and reference controls.
3.4 credits/generation
Create media with model-specific quality and reference controls.
2 credits/generation - 1K
Art-directed composition tuned for professional design work.
3 credits/generation - 1K
Aesthetic range, raw photorealism, and tunable style references.
7 credits/generation - 2K
Design-focused generation with especially strong typography.
4.25 credits/sec - 720p
Create media with model-specific quality and reference controls.
8.5 credits/sec - 720p
Create media with model-specific quality and reference controls.
15 credits/sec - 720p
Premium cinematic video with synchronized sound and reference control.
14.28 credits/sec - 720p
Create media with model-specific quality and reference controls.
5 credits/sec - 720p
Joint audio-video generation with strong prompt following, lip sync, and cinematic motion.
12 credits/sec - 720p
Multimodal directing with image, video, and audio references.
19.652 credits/sec - 720p
Create media with model-specific quality and reference controls.
6 credits/sec - 720p
High visual fidelity, prompt adherence, and convincing motion.
2.55 credits/sec - 720p
Fast scene generation with native audio. 1080p is upscaled from 720p.
4.25 credits/sec - 720p
Create media with model-specific quality and reference controls.
10 credits/sec - From source input
Edit an attached source video with a multimodal natural-language prompt.
12.75 credits/sec - 720p
Generate or edit video with native audio, start/end frames and image references. Automatic duration; charged by actual output.
3.4 credits/sec - 768P
Create media with model-specific quality and reference controls.
6.8 credits/sec - 768P
Create media with model-specific quality and reference controls.
4.25 credits/sec - 720p
Create media with model-specific quality and reference controls.
2 credits/sec - 720p
Fast text-to-video and image-to-video generation with native audio and rapid iteration.
2.55 credits/sec - 720p
Create media with model-specific quality and reference controls.
2.55 credits/sec - 720p
Transform an existing video with your instructions and references.
2.975 credits/sec - 768p
Create media with model-specific quality and reference controls.
3.825 credits/sec
Transform an existing video with your instructions and references.
2.55 credits/sec - 720p
Create media with model-specific quality and reference controls.
2.5 credits/sec - 720p
Accessible social video generation with crisp 720p and 1080p output.
2.55 credits/sec - From source input
Edit an existing clip with a prompt. Source up to 15 seconds / 50 MiB; output up to 720p.
2.55 credits/sec - 768p
Generate scenes with dialogue, ambience and sound effects. Minimum five seconds.
3 credits/sec - 768p
Expressive people, realistic human movement, and stylized visual effects.
5 credits/sec - 720p
Dependable natural motion, loops, and first/last-frame transitions.
6 credits/sec - 720p
Social-ready video with camera controls, transitions, multi-shot, and audio.
14.45 credits/sec - 720p
Create media with model-specific quality and reference controls.
6.8 credits/generation
Music and songs inspired by text or up to 10 images, around 3 minutes.
12.75 credits/generation
Instrumental music or songs with custom or generated lyrics, up to 6 minutes.
0.7055 credits/sec
Instrumentals and songs with a 5–300 second target duration and MP3/WAV output presets. Billed by output duration.
5 credits/min
Turn written scripts into spoken audio.
3.33 credits/1K characters
Turn written scripts into spoken audio.
1 credit/min
Turn speech into editable transcripts and captions.
1 credit/min
Turn speech into editable transcripts and captions.
Free - runs on your device
Run transcription locally on your device.
Free - runs on your device
Run transcription locally on your device.
Free - runs on your device
Run transcription locally on your device.
Free - runs on your device
Run transcription locally on your device.
Prices are app estimates at default settings. Duration, resolution and inputs change the final quote, which you confirm before generating.
A family groups the versions of one model line, such as a standard, Fast and Lite release. Open a family to compare its versions side by side, or choose an exact version above for its own settings and pricing.
xAIVideo
Create a short video shot from a supported prompt or reference image, then combine it with your own footage. Subclip is a separate product from the Grok app.
Compare versionsByteDanceVideo
Compare supported Seedance versions in one place and generate a shot for an editable video project. Input types and native-audio options depend on the endpoin
Compare versionsOpenAIImage
Generate or edit a still image for a thumbnail, scene or graphic, then place the result in your video project. Review spelling and fine details.
Compare versionsGoogleImage
Use supported Nano Banana image endpoints to build a scene or edit a reference. Compare the exact variant, resolution and price before generating.
Compare versionsGoogleVideo
Compare the Veo 3.1 variants available in Subclip, then generate a shot and finish the sequence on the timeline. Audio and output limits vary by endpoint.
Versions · 3