AI Talking Avatar

curl --request POST \
  --url https://api.goenhance.ai/api/v1/videos/generations \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "ai-talking-avatar",
  "image_url": "https://example.com/portrait.png",
  "audio_url": "https://example.com/speech.mp3",
  "prompt": "a woman speaking calmly to the camera",
  "resolution": "720p"
}
'

import requests

url = "https://api.goenhance.ai/api/v1/videos/generations"

payload = {
    "model": "ai-talking-avatar",
    "image_url": "https://example.com/portrait.png",
    "audio_url": "https://example.com/speech.mp3",
    "prompt": "a woman speaking calmly to the camera",
    "resolution": "720p"
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'ai-talking-avatar',
    image_url: 'https://example.com/portrait.png',
    audio_url: 'https://example.com/speech.mp3',
    prompt: 'a woman speaking calmly to the camera',
    resolution: '720p'
  })
};

fetch('https://api.goenhance.ai/api/v1/videos/generations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.goenhance.ai/api/v1/videos/generations",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'ai-talking-avatar',
    'image_url' => 'https://example.com/portrait.png',
    'audio_url' => 'https://example.com/speech.mp3',
    'prompt' => 'a woman speaking calmly to the camera',
    'resolution' => '720p'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.goenhance.ai/api/v1/videos/generations"

	payload := strings.NewReader("{\n  \"model\": \"ai-talking-avatar\",\n  \"image_url\": \"https://example.com/portrait.png\",\n  \"audio_url\": \"https://example.com/speech.mp3\",\n  \"prompt\": \"a woman speaking calmly to the camera\",\n  \"resolution\": \"720p\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.goenhance.ai/api/v1/videos/generations")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"ai-talking-avatar\",\n  \"image_url\": \"https://example.com/portrait.png\",\n  \"audio_url\": \"https://example.com/speech.mp3\",\n  \"prompt\": \"a woman speaking calmly to the camera\",\n  \"resolution\": \"720p\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.goenhance.ai/api/v1/videos/generations")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"ai-talking-avatar\",\n  \"image_url\": \"https://example.com/portrait.png\",\n  \"audio_url\": \"https://example.com/speech.mp3\",\n  \"prompt\": \"a woman speaking calmly to the camera\",\n  \"resolution\": \"720p\"\n}"

response = http.request(request)
puts response.read_body

{
  "code": 0,
  "msg": "Success",
  "data": {
    "img_uuid": "c12b656c-747a-44fd-9c80-add79b0c52d5"
  }
}

Talking Avatar

AI Talking Avatar

AI Talking Avatar. How it works — one portrait image plus one audio track: the person in the image speaks the audio, lip-synced.

⚠️ There is no duration parameter, and this endpoint rejects one. The output length follows your audio. Before any tokens are deducted, GoEnhance transfers audio_url to its own storage and measures the real duration — that measurement is what you are billed for, and it is also what enforces the 3-60s limit. Because the file is measured and then sent onward from GoEnhance’s storage, swapping the URL afterwards has no effect.

Audio requirements — 3-60 seconds, up to 50MB. Clear speech with little background noise gives the best lip sync.

Portrait requirements — up to 10MB. The face must be clearly visible, unobstructed and roughly front-facing.

Pricing — per second of audio, in tokens (USD at $0.02/token):

resolution	tokens/s	USD/s
540p	0.5	$0.01
720p	1	$0.02

A 30-second clip therefore costs 15 tokens at 540p, or 30 tokens at 720p.

Returns an img_uuid; poll GET /api/v1/jobs/detail (or use custom_callback_url) to get the generated video.

POST

api

videos

generations

AI Talking Avatar

curl --request POST \
  --url https://api.goenhance.ai/api/v1/videos/generations \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "ai-talking-avatar",
  "image_url": "https://example.com/portrait.png",
  "audio_url": "https://example.com/speech.mp3",
  "prompt": "a woman speaking calmly to the camera",
  "resolution": "720p"
}
'

import requests

url = "https://api.goenhance.ai/api/v1/videos/generations"

payload = {
    "model": "ai-talking-avatar",
    "image_url": "https://example.com/portrait.png",
    "audio_url": "https://example.com/speech.mp3",
    "prompt": "a woman speaking calmly to the camera",
    "resolution": "720p"
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'ai-talking-avatar',
    image_url: 'https://example.com/portrait.png',
    audio_url: 'https://example.com/speech.mp3',
    prompt: 'a woman speaking calmly to the camera',
    resolution: '720p'
  })
};

fetch('https://api.goenhance.ai/api/v1/videos/generations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.goenhance.ai/api/v1/videos/generations",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'ai-talking-avatar',
    'image_url' => 'https://example.com/portrait.png',
    'audio_url' => 'https://example.com/speech.mp3',
    'prompt' => 'a woman speaking calmly to the camera',
    'resolution' => '720p'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.goenhance.ai/api/v1/videos/generations"

	payload := strings.NewReader("{\n  \"model\": \"ai-talking-avatar\",\n  \"image_url\": \"https://example.com/portrait.png\",\n  \"audio_url\": \"https://example.com/speech.mp3\",\n  \"prompt\": \"a woman speaking calmly to the camera\",\n  \"resolution\": \"720p\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.goenhance.ai/api/v1/videos/generations")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"ai-talking-avatar\",\n  \"image_url\": \"https://example.com/portrait.png\",\n  \"audio_url\": \"https://example.com/speech.mp3\",\n  \"prompt\": \"a woman speaking calmly to the camera\",\n  \"resolution\": \"720p\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.goenhance.ai/api/v1/videos/generations")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"ai-talking-avatar\",\n  \"image_url\": \"https://example.com/portrait.png\",\n  \"audio_url\": \"https://example.com/speech.mp3\",\n  \"prompt\": \"a woman speaking calmly to the camera\",\n  \"resolution\": \"720p\"\n}"

response = http.request(request)
puts response.read_body

{
  "code": 0,
  "msg": "Success",
  "data": {
    "img_uuid": "c12b656c-747a-44fd-9c80-add79b0c52d5"
  }
}

Headers

Authorization

string

Body

application/json

model

enum<string>

required

Model name. Must be ai-talking-avatar.

Available options:

ai-talking-avatar

image_url

string<uri>

required

Portrait image of the speaker (up to 10MB). Required. The face must be clearly visible, unobstructed and roughly front-facing.

audio_url

string<uri>

required

Speech audio to lip-sync to (3-60 seconds, up to 50MB). Required. Its measured duration sets both the output length and the price.

prompt

string

default:person talking

Optional description of the desired performance, e.g. a woman speaking calmly to the camera.

resolution

enum<string>

default:540p

Output resolution. 720p costs twice as much per second as 540p.

Available options:

540p,

720p

custom_callback_url

string<uri>

Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt.

Example:

"https://your-server.com/goenhance/callback"

Response

code

integer

required

msg

string

required

data

object

required

Show child attributes

Getting started

API

AI Talking Avatar

Headers

Body

Response