Kling MCP: make Kling videos from Claude, ChatGPT and Cursor

Kling v3.0 Pro is Kuaishou's premium video generation model, offering higher visual quality than the Standard tier.

Kling v3.0 Standard is a video generation model from Kuaishou. It supports text-to-video and image-to-video workflows, with first-frame and last-frame control for guided scene composition.

Kling Video O1 is a video generation model from Kuaishou. It supports text and image inputs with video output, enabling text-to-video and image-to-video workflows.

Animate a still image (first or first+last frame) into a 5- or 10-second video at 720p/1080p, guided by a text prompt. Strengths: the cheapest tier with native audio (1080p, 1 unit/s) and half the 3.0 rate for silent clips. Limits: 5 or 10 s only, 720p is silent only (native audio requires 1080p), no 4K, no multi-shot. Returns outputs[].url (MP4, 30-day link) with the generated duration; the output keeps the image's aspect ratio and optional native audio. Suited for: product shots to motion, character animation, photo-to-clip social content, keyframe-driven transitions.

Animate a still image (first or first+last frame) into a 5- or 10-second video at 720p/1080p, guided by a text prompt. Strengths: the cheapest Kling tier (0.3/0.5 units/s) with first-and-last-frame control at 1080p. Limits: silent only, 5 or 10 s only, last frame needs 1080p, no 4K. Returns outputs[].url (MP4, 30-day link) with the generated duration; the output keeps the image's aspect ratio. Suited for: product shots to motion, character animation, photo-to-clip social content, keyframe-driven transitions.

Turn a text prompt into a 5- or 10-second video at 720p/1080p. Strengths: the cheapest Kling tier (0.3/0.5 units/s) with first-and-last-frame control at 1080p. Limits: silent only, 5 or 10 s only, last frame needs 1080p, no 4K. Returns outputs[].url (MP4, 30-day link) with the generated duration. Supports aspect ratios 16:9, 9:16, 1:1. Suited for: short-form social clips, ads and product b-roll, storyboards, concept previews.

Animate a still image (first frame) into a 3-15 second video at 720p/1080p, guided by a text prompt. Strengths: the fast 3.0 tier: always ships native audio, any 3-15 s length, cheaper than 3.0 with audio. Limits: no 4K, no last frame, no multi-shot switch, and audio cannot be turned off. Returns outputs[].url (MP4, 30-day link) with the generated duration; the output keeps the image's aspect ratio. Suited for: product shots to motion, character animation, photo-to-clip social content, keyframe-driven transitions.

Turn a text prompt into a 3-15 second video at 720p/1080p. Strengths: the fast 3.0 tier: always ships native audio, any 3-15 s length, cheaper than 3.0 with audio. Limits: no 4K, no last frame, no multi-shot switch, and audio cannot be turned off. Returns outputs[].url (MP4, 30-day link) with the generated duration. Supports aspect ratios 16:9, 9:16, 1:1. Suited for: short-form social clips, ads and product b-roll, storyboards, concept previews.

Turn a text prompt into a 5- or 10-second video at 720p/1080p. Strengths: the cheapest tier with native audio (1080p, 1 unit/s) and half the 3.0 rate for silent clips. Limits: 5 or 10 s only, 720p is silent only (native audio requires 1080p), no 4K, no multi-shot. Returns outputs[].url (MP4, 30-day link) with the generated duration. Supports aspect ratios 16:9, 9:16, 1:1, optional native audio. Suited for: short-form social clips, ads and product b-roll, storyboards, concept previews.

Animate a character image with the body motion of a reference video (3-30 s, one person, single take), keeping the character's look and optionally the clip's original audio, at 720p/1080p. Strengths: the budget motion tier at roughly half the 3.0 rate (0.5/0.8 units/s), original audio kept. Limits: lower fidelity than 3.0, no 4K, needs a clean single-person reference clip and the output can be shorter than it. Returns outputs[].url (MP4, 30-day link) with the generated duration, which follows the usable motion in the reference (and may be shorter). Supports character_orientation to follow the image or the video framing. Suited for: dance and performance transfer, character animation from a single photo, avatar motion clips.

Animate a character image with the body motion of a reference video (3-30 s, one person, single take), keeping the character's look and optionally the clip's original audio, at 720p/1080p. Strengths: the 3.0 motion model: the highest motion fidelity and character consistency, original audio kept. Limits: 0.9/1.2 units/s, no 4K, needs a clean single-person reference clip and the output can be shorter than it. Returns outputs[].url (MP4, 30-day link) with the generated duration, which follows the usable motion in the reference (and may be shorter). Supports character_orientation to follow the image or the video framing. Suited for: dance and performance transfer, character animation from a single photo, avatar motion clips.