Header Logo

Docs

Start

Header Logo

Start

Header Logo

Docs

Start

All Models

Meituan logo

LongCat Avatar 1.5

LongCat Avatar 1.5 turns a portrait and speech audio into a talking-avatar video, with optional motion reference.

Price is per video output second, rounded up.
Offering
Price
480p
$0.06
720p
$0.08
1080p
$0.10

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

LongCat Avatar 1.5

LongCat Avatar 1.5 is Meituan’s talking-avatar model. You give it a portrait and a speech recording, and it returns a lip-synced video of that person. An optional motion reference can steer gesture and posture instead of a default idle. It is the default Studio avatar engine.

It is not a general text-to-video model. The face comes from the still; the words come from the audio you upload. Native output is 480p. 720p and 1080p are upscaled. Aspect ratio can be auto, 16:9, or 9:16. Metering starts at five seconds; the clip can follow a longer voiceover than a typical cinematic generate.

What it's good for

Course presenters, product explainers, and support avatars. A clean, fairly frontal portrait and dry speech work best. It will not invent a character from a text prompt, and it will not write the script.

Model ID

meituan/longcat-avatar-1.5

Output Type

Video

Pricing

From $0.06/s

Provider

Meituan

Hosting

Protoface

LongCat Avatar 1.5

LongCat Avatar 1.5 is Meituan’s talking-avatar model. You give it a portrait and a speech recording, and it returns a lip-synced video of that person. An optional motion reference can steer gesture and posture instead of a default idle. It is the default Studio avatar engine.

It is not a general text-to-video model. The face comes from the still; the words come from the audio you upload. Native output is 480p. 720p and 1080p are upscaled. Aspect ratio can be auto, 16:9, or 9:16. Metering starts at five seconds; the clip can follow a longer voiceover than a typical cinematic generate.

What it's good for

Course presenters, product explainers, and support avatars. A clean, fairly frontal portrait and dry speech work best. It will not invent a character from a text prompt, and it will not write the script.