Automate Runway ML for free on Stepper

Generate Video from Image

Generate a video from a reference image using Runway's video generation models. Returns the output video URL when generation is complete.

• 5 parameters
• Model
• Image URL
• Prompt
• Aspect Ratio
• Duration (seconds)

Generate Video from Text

Generate a video from a text prompt using Runway's text-to-video models. Returns the output video URL when generation is complete.

• 4 parameters
• Model
• Prompt
• Aspect Ratio
• Duration (seconds)

Transform Video

Transform an existing video using Runway's video-to-video model (Gen 4 Aleph). Returns the transformed output video URL when generation is complete.

• 5 parameters
• Video URL
• Prompt
• Reference Image URL
• Aspect Ratio
• Duration (seconds)

Animate Character

Drive a character's facial and body movements using a reference performance video with Runway's Act Two model. Returns the output video URL when generation is complete.

• 2 parameters
• Character Image/Video URL
• Performance Video URL

Generate Image

Generate one or more images from a text prompt and/or reference image using Runway's image generation models. Returns the output image URL(s) when generation is complete.

• 4 parameters
• Model
• Prompt
• Reference Image URL
• Aspect Ratio

Generate Speech

Generate realistic speech audio from text using Runway's text-to-speech model. Returns the output audio URL when generation is complete. Costs approximately 1 credit per 50 characters.

• 2 parameters
• Text
• Voice

Generate Sound Effect

Generate a sound effect from a text description using Runway's sound effect model. Returns the output audio URL when generation is complete. Costs approximately 1 credit per 6 seconds.

• 2 parameters
• Description
• Duration (seconds)

Convert Voice

Convert the voice in an audio or video file to a different voice preset using Runway's speech-to-speech model. Returns the output audio URL when generation is complete. Costs approximately 1 credit per 2 seconds.

• 2 parameters
• Audio/Video URL
• Target Voice

Dub Audio

Dub the speech in an audio or video file into a different target language using Runway's voice dubbing model. Returns the dubbed output URL when generation is complete. Costs approximately 1 credit per 2 seconds.

• 2 parameters
• Audio/Video URL
• Target Language

Isolate Voice

Isolate the voice track from background noise and music in an audio or video file using Runway's voice isolation model. Returns the cleaned audio URL when generation is complete. Costs approximately 1 credit per 6 seconds.

• 1 parameters
• Audio/Video URL

Make HTTP Request

Make an HTTP request to any URL with full control over method, headers, and body.