Audio Cleaner (Text To Speech) API - Complete Integration Guide

Overview

Key Features

• Rich voice parameter customization: configure voice_id, emotion, speed, and language for personalized speech styles.
• Diverse voice and language options: integrated multi-language, multi-voice library with continuous updates for different use cases.
• Fast response: TTS tasks are processed quickly, often generating high-quality audio in seconds for batch or real-time scenarios.
• Powerful AI speech modeling: advanced AI models restore text emotion and intonation for natural, human-like voice output.

Authentication

All API requests require an api-key. Include your API key in the request header:

API Host: https://audiocleaner.ai/

api-key: YOUR_API_KEY

Credit Billing Rules

• Rule: 1 credit is charged for every 100 characters, and any remainder under 100 still counts as 1 credit.
• Example: 215 characters consumes 3 credits.
• Example: 60 characters consumes 1 credit.

1. Create TTS Task

Endpoint

POST /audio/api/v1/api-keys/tts/task/create

Request Headers

Request Parameters (Body · JSON)

Supported Languages

Supported Speed Multipliers

Supported Emotion Parameters

• Note: language and speed options can be extended according to actual TTS capabilities.

Parameter Example (JSON)

{
  "voice_id": 2072,
  "emotion": 0,
  "speed": 1,
  "language": "en",
  "text": "Faced with growing backlash, US President Donald Trump appears to have removed a controversial Truth Social post depicting himself as a Jesus-like figure.\n\nThe AI-generated image, which showed Trump appearing to heal a sick man in a hospital bed, sparked fierce backlash from both sides of the US political spectrum, including from some of Trump's most ardent supporters."
}

Response Format (Unified)

{
  "code": 100000,
  "data": {
    "job_id": "33b6251d7ba94edea8361c318736e746"
  },
  "message": "Request Success"
}

Response Code (code) Description

Example

curl --location --request POST 'https://audiocleaner.ai/audio/api/v1/api-keys/tts/task/create' \
  --header 'Content-Type: application/json' \
  --header 'api-key: YOUR_API_KEY' \
  --data-raw '{
    "voice_id": 2072,
    "emotion": 0,
    "speed": 1,
    "language": "en",
    "text": "Hello from Audio Cleaner TTS API."
  }'

2. Query TTS Task Status

Interface Description

• Use this API to query task status. Request headers must include api-key.
• The backend validates API key legality, including but not limited to key existence, rate limit, concurrency limit, credit sufficiency, and task existence.
• The API returns different task states and explicit error codes for failure cases.

Endpoint

POST /audio/api/v1/api-keys/tts/task/get

Request Headers

Request Parameters (Body · JSON)

Response Format (Success Example)

{
  "code": 100000,
  "data": {
    "status": "waiting/success/failed",
    "output": ""
  },
  "message": "Request Success"
}

Response Field Description

Response Code (code) Description

Example

curl --location --request POST 'https://audiocleaner.ai/audio/api/v1/api-keys/tts/task/get' \
  --header 'Content-Type: application/json' \
  --header 'api-key: YOUR_API_KEY' \
  --data-raw '{
    "global_id": "59063d399a3749f290a2d9fb4e75ddc3"
  }'

3. Download TTS Voice Library (Voice List)

Interface Description

• Returns only voice information visible/available to the current account.
• Returns JSON with all fields needed by business usage (such as image/audio URLs and base attributes).
• Includes key field descriptions such as gender and age.
• After login, click the Developer menu, open Playground, and choose AI Voice Generator.

Response Format (Example)

{
  "code": 100000,
  "data": {
    "total": 159,
    "records": [
      {
        "id": 2072,
        "gender": 2,
        "language": "en",
        "age": 2,
        "emotion": [
          "chat",
          "customerservice",
          "narration-professional",
          "newscast-casual",
          "newscast-formal",
          "cheerful",
          "empathetic",
          "angry",
          "sad",
          "excited",
          "friendly",
          "terrified",
          "shouting",
          "unfriendly",
          "whispering",
          "hopeful"
        ],
        "name": "madison",
        "display_name": "Madison"
      }
    ]
  },
  "message": "Request Success"
}

Field Description (Key)

Recommended Usage Flow

• Call the voice list API to fetch voice_id and available parameters.
• Call the create-task API, submit text, and get job_id.
• Poll the task status API until status = success.
• Read output and download/play the generated audio.

FAQ