Text to Speech Actor

An Apify Actor that converts text to speech using AI-powered voice synthesis technology. Simply provide the text you want to convert, along with language and voice preferences, and the Actor will generate a high-quality audio file for you.

What This Tool Does

This Actor connects to the MultipleWords text-to-speech API to convert written text into natural-sounding speech. It accepts text input along with language and voice configuration, processes the request through the API, and returns a downloadable audio file along with detailed metadata about the voice generation.

Key Features:

🎙️ Convert text to natural-sounding speech
🚀 Fast and automated audio generation
📦 Structured output with audio URLs and metadata
🔄 Reliable error handling and validation
📊 Complete generation details and timestamps
🌍 Support for multiple languages and voices

Purpose & Use Cases

This tool is designed to help individuals, businesses, and developers automate text-to-speech conversion for various purposes:

Content Creation

• Generate voiceovers for videos and presentations
• Create audio versions of blog posts and articles
• Produce podcast introductions and outros
• Generate narration for e-learning courses

Accessibility

• Convert written content to audio for visually impaired users
• Create audio descriptions for multimedia content
• Generate spoken versions of documents and reports
• Make content accessible through audio format

Business & Marketing

• Create automated phone system messages
• Generate voice prompts for IVR systems
• Produce marketing audio content
• Create audio advertisements and announcements

Development & Automation

• Integrate text-to-speech into automated workflows
• Batch convert multiple text documents to audio
• Create audio content programmatically via API integration
• Generate dynamic voice content for applications

Media Production

• Quickly generate voiceovers for video projects
• Create multiple voice variations for A/B testing
• Produce audio content for social media
• Generate voice samples and demos

Input Parameters

The Actor requires the following input:

text (Required)

Type: String
Description: The text content you want to convert to speech. Can be a single sentence, paragraph, or multiple paragraphs.
Example: "Technology that thinks with you, builds for you, and moves you forward. Welcome to the future—simple, smart, and powered by AI."
Best Practices:

• Use clear, well-formatted text
• Include proper punctuation for natural pauses
• Break long content into paragraphs for better audio flow
• Avoid special characters that may cause issues

language_id (Required)

Type: String
Description: Language identifier for the speech synthesis (e.g., 'en' for English, 'es' for Spanish, 'fr' for French).
Default: "en"
Example: "en", "es", "fr", "de"

voice_id (Required)

Type: String
Description: Voice identifier specifying the voice type to use (e.g., 'male' or 'female').
Default: "male"
Example: "male", "female"

user_id (Required)

Type: Integer
Description: User identifier for the API authentication.
Default: 663569
Example: 663569

isPro (Required)

Type: Integer
Description: Pro account flag indicating whether to use premium features (0 = No, 1 = Yes).
Default: 0
Valid Values: 0 or 1

Output Structure

The Actor returns structured data containing the generated audio file information:

{
  "status": "success",
  "file_name": "voice_20260127_072606_295b10fe.mp3",
  "access_url": "https://multiplewords.nyc3.cdn.digitaloceanspaces.com/text_to_voice/voice_20260127_072606_295b10fe.mp3",
  "voice_used": "en-AU-WilliamNeural",
  "details": {
    "id": 328186,
    "video_url": "https://multiplewords.nyc3.cdn.digitaloceanspaces.com/text_to_voice/voice_20260127_072606_295b10fe.mp3",
    "source_video_url": "",
    "video_description": "Technology that thinks with you, builds for you, and moves you forward.\nWelcome to the future—simple, smart, and powered by AI.",
    "video_name": "Technology that thinks with you, builds for you, and moves you forward.\nWelcome to the future—simple, smart, and powered by AI.",
    "video_description_to": "",
    "fps": 10,
    "video_length": 5,
    "creativity": 8.5,
    "isMusic": true,
    "isPro": false,
    "video_thumbnail": "https://multiplewords.nyc3.digitaloceanspaces.com/mw_assets/mw_logo_square_.jpg",
    "video_created_at": "2026-01-27T07:26:07.665739Z",
    "video_updated_at": "2026-01-27T07:26:07.665767Z",
    "engine": 35,
    "url_slug": "",
    "job_key": "0",
    "job_status": 1,
    "rating": 0,
    "feedback": "",
    "extra_1": null,
    "extra_2": null,
    "extra_3": null,
    "extra_4": null,
    "extra_5": null,
    "extra_6": null,
    "attempts": 3,
    "is_public": true,
    "isIndexed": false,
    "is_active": true,
    "number_of_times_played": 1,
    "user_id": 663569,
    "video_category_id": 1,
    "language_id": 49
  }
}

Output Fields Explained

• status: Success indicator ("success" = successful conversion)
• file_name: Name of the generated audio file
• access_url: Direct URL to download the generated audio file (MP3 format)
• voice_used: The specific voice model used for synthesis (e.g., "en-AU-WilliamNeural")
• details: Complete metadata about the audio generation
  • id: Unique identifier for the generated audio
  • video_url: URL to the audio file (same as access_url)
  • video_length: Duration of the audio in seconds
  • video_created_at: Timestamp when the audio was created
  • job_status: Status of the generation job
  • user_id: User identifier used for the request
  • language_id: Language identifier used

How to Use

Running Locally

1. Install dependencies:

$npm install

2. Run the Actor:

$apify run

3. Provide input when prompted, or create an input file in storage/key_value_stores/default/INPUT.json:

{
  "language_id": "en",
  "voice_id": "male",
  "user_id": 663569,
  "isPro": 0,
  "text": "Technology that thinks with you, builds for you, and moves you forward. Welcome to the future—simple, smart, and powered by AI."
}

Deploy to Apify Platform

1. Login to Apify:

$apify login

2. Deploy the Actor:

$apify push

3. Run on Apify Console:

   • Go to Actors -> My Actors
   • Select your Text to Speech Actor
   • Enter your text and configuration in the input form
   • Click "Start" to generate your audio file

Using via API

Once deployed, you can call the Actor via Apify API:

curl -X POST "https://api.apify.com/v2/acts/YOUR_USERNAME~text-to-speech/run-sync" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "language_id": "en",
    "voice_id": "male",
    "user_id": 663569,
    "isPro": 0,
    "text": "Create a professional voiceover for a tech product launch announcement"
  }'

Integration Examples

With Make (Integromat)

• Connect the Actor to your Make workflows
• Automatically generate voiceovers when new content is created
• Send generated audio files to storage services or email
• Create automated content pipelines with text-to-speech

With Zapier

• Trigger audio generation from form submissions
• Automatically add audio files to Google Drive or Dropbox
• Send audio notifications via Slack or email
• Convert blog posts to audio automatically

With Custom Applications

• Integrate via Apify API into your web applications
• Batch convert multiple text documents to audio
• Create automated voiceover workflows
• Build custom text-to-speech services

Technical Details

• Runtime: Node.js 18+
• Dependencies: Apify SDK v3.5.2+
• API Endpoint: https://shorts.multiplewords.com/mwvideos/api/voice_from_text
• Request Method: POST
• Content Type: multipart/form-data
• Response Format: JSON
• Audio Format: MP3

Error Handling

The Actor includes comprehensive error handling:

• Validates all required input parameters before processing
• Handles API errors gracefully with detailed error messages
• Provides informative error messages in logs
• Returns appropriate exit codes for debugging
• Validates API response status and structure

Resources

• Apify SDK Documentation
• Apify Platform Documentation
• Apify Academy - Node.js Tutorials
• Join Apify Developer Community

Support

For issues, questions, or feature requests, please refer to the Apify documentation or community forums.

---

Built with ❤️ using Apify SDK