Characters（lip-synthesis）

POST

/hedra/api/v1/characters

A lip-synthesis interface from Hedra.
This interface synthesizes static portrait photos and speech to produce a final dynamic video of a person speaking. The video duration is determined by the audio duration and is billed by the second.

Price：0.01 PTC/second

Request

Header Params

Authorization

string

optional

Example:

Bearer {{YOUR_API_KEY}}

Content-Type

string

optional

Example:

application/json

Body Params application/json

avatarImage

string

required

url returned by the Portal interface.

audioSource

string

required

audio

voiceUrl

string

required

url returned by the Audio interface.

Example

   {
        "avatarImage": "",
        "audioSource": "audio",
        "voiceUrl": ""
    }

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/hedra/api/v1/characters' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
        "avatarImage": "",
        "audioSource": "audio",
        "voiceUrl": ""
    }'

Responses

🟢200Success

application/json

Body

object {0}

Example

{}

Modified at 2025-06-03 03:19:16

Portrait（Upload）

Fetch（Result）