Hedra 角色动画

角色动画，音频完美同步。让肖像栩栩如生，展现自然表情与动作。

Authentication

To access Hedra through Doitong API, use your Doitong API key. Include it in the GraphQL mutation or REST API headers.

// GraphQL Header
{
  "Authorization": "Bearer YOUR_API_KEY"
}

// REST Header
"X-API-Key": "YOUR_API_KEY"

Quick Start

Get started with Hedra Lip Sync API in just a few minutes. Follow these simple steps to generate your first avatar.

Step 1: Get Your API Key

Sign up for a Doitong account and navigate to your dashboard to generate an API key.

Step 2: Make Your First Request

Use one of the code examples below to make your first API call.

curl -X POST https://api.doitong.com/graphql \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "query": "mutation Generate($input: GenerateInput!) { generate(input: $input) { id status type provider url metadata creditCost } }",
    "variables": {
      "input": {
        "type": "AVATAR",
        "provider": "hedra",
        "input": {
          "text": "Hello, welcome to our platform!",
          "avatarId": "professional-1"
        },
        "options": {
          "voice": "en-US-neural"
        }
      }
    }
  }'

const response = await fetch('https://api.doitong.com/graphql', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer YOUR_API_KEY'
  },
  body: JSON.stringify({
    query: `
      mutation GenerateAvatar($input: AvatarGenerationInput!) {
        generateAvatar(input: $input) {
          id
          status
          videoUrl
        }
      }
    `,
    variables: {
      input: {
        service: 'hedra',
        text: 'Hello, welcome to our platform!',
        avatarId: 'professional-1',
        voice: 'en-US-neural'
      }
    }
  })
});

const data = await response.json();
console.log('Avatar Video:', data.data.generateAvatar);

import requests
import json

url = "https://api.doitong.com/graphql"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer YOUR_API_KEY"
}

query = """
mutation Generate($input: GenerateInput!) {
  generate(input: $input) {
    id
    status
    type
    provider
    url
    metadata
    creditCost
  }
}
"""

variables = {
    "input": {
        "type": "AVATAR",
        "provider": "hedra",
        "input": {
            "text": "Hello, welcome to our platform!",
            "avatarId": "professional-1"
        },
        "options": {
            "voice": "en-US-neural"
        }
    }
}

response = requests.post(url, json={
    "query": query,
    "variables": variables
}, headers=headers)

data = response.json()
print("Result:", data["data"]["generate"])

mutation Generate($input: GenerateInput!) {
  generate(input: $input) {
    id
    status
    type
    provider
    url
    metadata
    creditCost
    createdAt
  }
}

# Variables
{
  "input": {
    "type": "AVATAR",
    "provider": "hedra",
    "input": {
      "text": "Hello, welcome to our platform!",
      "avatarId": "professional-1"
    },
    "options": {
      "voice": "en-US-neural",
      "language": "en",
      "version": "hedra-1.0"
    }
  }
}

Pricing

The Hedra Lip Sync API uses a credit-based pricing model. Credits are consumed based on the complexity and duration of the generated content.

API Endpoints

The Hedra Lip Sync API is available through our unified GraphQL endpoint.

GraphQL Endpoint

POST https://api.doitong.com/graphql

REST Endpoint

POST https://api.doitong.com/v1/avatar

Parameters

Available parameters for Hedra Lip Sync API requests:

Response Format

All API responses follow a consistent format:

Success Response

{
  "data": {
    "avatar": {
      "id": "abc123xyz",
      "status": "processing",
      "url": null,
      "webhookUrl": "https://your-webhook.com/callback",
      "createdAt": "2024-01-01T00:00:00Z"
    }
  }
}

Completed Response

{
  "data": {
    "avatar": {
      "id": "abc123xyz",
      "status": "completed",
      "url": "https://cdn.doitong.com/outputs/abc123xyz.mp3",
      "duration": null,
      "createdAt": "2024-01-01T00:00:00Z"
    }
  }
}

Error Handling

The API uses standard HTTP status codes and returns detailed error messages.

Common Error Codes

Error Response Format

{
  "errors": [
    {
      "message": "Insufficient credits for this operation",
      "extensions": {
        "code": "INSUFFICIENT_CREDITS",
        "creditsRequired": 100,
        "creditsAvailable": 50
      }
    }
  ]
}

Webhooks

Receive real-time notifications when your avatar generation is complete.

Setting Up Webhooks

Include a <code>webhookUrl</code> parameter in your request to receive a POST notification when processing is complete.

Webhook Payload

{
  "id": "abc123xyz",
  "status": "completed",
  "url": "https://cdn.doitong.com/outputs/abc123xyz.mp3",
  "service": "hedra",
  "createdAt": "2024-01-01T00:00:00Z",
  "completedAt": "2024-01-01T00:01:00Z",
  "metadata": {
    "duration": null,
    "width": null,
    "height": null
  }
}

Webhook Security

All webhook requests include a signature header for verification:

X-Doitong-Signature: sha256=abc123...

Rate Limits

To ensure fair usage and system stability, the following rate limits apply:

Best Practices

1. Optimize Your Prompts

Write clear, descriptive prompts for best results:

• Be specific about visual elements, style, and mood
• Include details about lighting, camera angles, and composition
• Avoid contradictory or impossible requests

2. Handle Async Processing

Generation is asynchronous. Implement proper polling or webhooks:

// Polling example
async function pollStatus(jobId) {
  let status = 'processing';
  while (status === 'processing') {
    await sleep(2000); // Wait 2 seconds
    const result = await checkJobStatus(jobId);
    status = result.status;
  }
  return result;
}

3. Error Recovery

Implement retry logic with exponential backoff:

async function retryWithBackoff(fn, maxRetries = 3) {
  for (let i = 0; i < maxRetries; i++) {
    try {
      return await fn();
    } catch (error) {
      if (i === maxRetries - 1) throw error;
      await sleep(Math.pow(2, i) * 1000);
    }
  }
}

4. Monitor Credit Usage

Track your credit consumption to avoid interruptions:

• Check credit balance before large batch operations
• Set up alerts for low credit thresholds
• Implement credit-aware request queuing

Ready to Get Started?

Join thousands of developers using Hedra Lip Sync API to create amazing content