Ondoku User Guide

This article introduces the specifications of Ondoku.

Table of Contents

1. Overview
2. How to Use
3. Registration and Login
4. Character Count and Renewal
5. Recommended Environment for Use
6. Feature Descriptions
   1. Text-to-Speech Feature
   2. Download Feature
   3. Conversation Feature
   4. Image-to-Speech Feature
   5. Splitting Feature
   6. Dictionary Feature
   7. Sharing Feature
   8. Deletion Feature
   9. History
7. Specifications of the Text-to-Speech Feature
   1. How Character Counts are Consumed
   2. Input Character Restrictions
   3. Intonation
   4. Translation of Foreign Languages
   5. How to have Romaji Read Aloud
8. Usage Plans
   1. Free Plan
   2. Paid Plans
   3. Paid Plan Fees
   4. Payment Methods for Paid Plans
   5. Invoices and Receipts
9. Commercial Use and Prohibited Acts
10. Credit Attribution
11. Security
12. Technical Support
13. Frequently Asked Questions

1. Overview

Ondoku is a web-based service that uses AI to convert text into speech. No installation is required, and it can be used within a web browser. While it is a type of generative AI, it is not an LLM (Large Language Model).

2. How to Use

• Can be used anywhere as long as you have an internet connection and can browse the web.
• While a dedicated app is under consideration, it can be used like an app through the following methods:
• iPhone: How to easily use it from the home screen like an app on iPhone [No installation required]
• Android: "How to install Ondoku [Android devices]"

3. Registration and Login

• Can be used without registration. However, registering offers benefits such as an increased character limit.
• Free Member Registration
• Login

4. Character Count and Renewal

• Unused characters cannot be carried over.
• The character count is renewed on the next renewal date.
• The next renewal date can be checked from the Settings screen after logging in.

5. Recommended Environment for Use

• For a single text box, the recommended character counts are: Normal: 5,000 characters; When using SSML: 3,000 characters.
• Recommended browser: Latest version of Google Chrome

6. Feature Descriptions

6.1 Text-to-Speech Feature

• Enter text into the text box, set the language, speaker, speed, and pitch, and click the read-aloud button to create audio on the spot.

6.2 Download Feature

• A feature to download the created audio.
• Downloadable in MP3 format on the TOP page.
• Downloadable in MP3 and WAV formats from the History.

6.3 Conversation Feature

• Allows for the creation of dialogue-style audio with multiple speakers.
• Register speaker settings in advance.
• You can create audio with interactions between multiple speakers.
• Frequently used for listening practice audio and similar content.

6.4 Image-to-Speech Feature

• A feature that reads text from an image and converts it into speech.
• Supported image formats: .jpg, .png

6.5 Splitting Feature

• A feature for previously created audio that allows you to set a specific pause duration and download the file split at points where pauses longer than that duration occur.
• Available from the History screen.

6.6 Dictionary Feature

• A feature to customize the pronunciation of specific words or phrases.
• The dictionary feature is only reflected for the language: Japanese.
• Available from the "Dictionary" tab in the menu.

6.7 Sharing Feature

• A feature to share created audio.
• You can embed tags or share URLs.
• When shared, anyone with the URL can access it, but it will not be indexed by search engines.

6.8 Deletion Feature

• A feature to delete created audio.
• The storage period for audio varies by membership level, but it can be deleted manually at any time.
• There is a feature to delete items one by one and a "Bulk Deletion Feature" to delete all history at once.

6.9 History

• You can check the history of your past speech generations.
• History can be deleted at any time using the deletion feature.
• When a past generation is deleted from history, the read text and the generated audio data are deleted from the server.
  How to use the Deletion Feature and Bulk Deletion Feature and precautions. Deleting text and data from history and the server

7. Specifications of the Text-to-Speech Feature

7.1 How Character Counts are Consumed

• Clicking the read-aloud button consumes the available character count.
• Characters are counted as one character per character.
  Whether or not the file is downloaded does not matter. This is how Ondoku counts characters! What about punctuation? English? Chinese? How are they counted?
• If "the same text, same language, same speaker, and same settings" exist in the history, the available character count will not be consumed. [Response to Ondoku Request] I want character counts to not be consumed when making corrections

7.2 Input Character Restrictions

• There is no limit to the number of characters that can be entered or converted at one time.
• Using excessively long text is not recommended as it may cause errors.
• The recommended character counts are as stated in "5. Recommended Environment for Use."
• The reading function strictly reads "text."
• Symbols may not be read correctly, so it is recommended to replace them with words.
• Emojis may not be read or may cause errors, so entering them is discouraged.

7.3 Intonation

• While intonation cannot be directly adjusted, there are ways to adjust or refine it.
  "Methods to try when you want to adjust intonation and inflection"
• SSML support varies depending on the specific voice.

7.4 Foreign Language Translation

• Ondoku itself does not have a translation function.
• If you enter Japanese and use a foreign language voice to read it, it will only sound like that language and will not be the actual foreign language (e.g., Spanish or Vietnamese). "How to create audio in foreign languages"

7.5 Reading Romaji

• There are three ways to have Romaji pronounced correctly.
  1. Use a multilingual-supported voice.
  2. Use a Japanese voice.
  3. Use phonics.

"Three ways to make AI voice "Ondoku" pronounce Romaji correctly"

8. Usage Plans

8.1 Free Plan

• Non-member: Free up to 1,000 characters per month
• Free Member: Free up to 5,000 characters per month

8.2 Paid Plans

• Basic: 200,000 characters/month, 300 images/month
• Value: 450,000 characters/month, 1,000 images/month
• Premium: 1,000,000 characters/month, 2,500 images/month
• Business Basic: 2,400,000 characters, 3,600 images
• Business Value: 5,400,000 characters, 12,000 images
• Business Premium: 12,000,000 characters, 30,000 images

8.3 Paid Plan Fees

• Monthly plans and business plans are available.
• Refer to the Ondoku pricing page for details.
• Ondoku: Pricing Page, Business Plan

8.4 Payment Methods for Paid Plans

• Credit Card, Debit Card, Link payment (Stripe) are subscriptions.
• Bank transfer (annual payment, Japanese bank accounts only) is not a subscription.

8.5 Invoices and Receipts

• For Credit/Debit Cards:
• Invoice and receipt emails are sent automatically upon payment completion.
• From the Ondoku settings page, a combined card usage statement and receipt is available.
• For Bank Transfers: Estimates, invoices, and receipts (after payment) are available from the Ondoku settings page.

9. Commercial Use and Prohibited Acts

• Commercial use is permitted. However, as there are restrictions depending on the method of use, please see the following article for details.
• Explanatory article on commercial use: Ondoku: About commercial use and prohibited items
• Sharing accounts or possessing multiple free accounts is prohibited.
• Possessing multiple paid accounts is permitted.
• However, for corporations, one account can be shared across up to 10 terminals.

10. Credit Attribution

• Credit attribution is required when using audio data for free.
• For paid plans, credit attribution is not required during the paid plan subscription period.
• If you continue to use the audio after switching from a paid plan to a free plan, credit attribution is required.
• For business plans, credit attribution is not required even after cancellation.

11. Security

• Security-related content is published in the lists below:
  "Cloud Service Level Checklist" by the Ministry of Economy, Trade and Industry
  "How to Build Secure Websites, 7th Revised Edition" by IPA (Information-technology Promotion Agency, Japan)
• Other detailed information is explained below:
  "Can you fill out answers for security-related documents?"
  "What is the security of Ondoku like? Detailed answers regarding servers, etc."

12. Technical Support

• Provision of support information such as troubleshooting for errors and login issues.

13. Frequently Asked Questions

• Provides answers to common questions such as owning multiple accounts, text-to-speech errors, and language support.

■ AI voice synthesis software "Ondoku"

"Ondoku" is an online text-to-speech tool that can be used with no initial costs.

• Supports approximately 50 languages, including Japanese, English, Chinese, Korean, Spanish, French, and German
• Available from both PC and smartphone
• Suitable for business, education, entertainment, etc.
• No installation required, can be used immediately from your browser
• Supports reading from images

To use it, simply enter text or upload a file on the site. A natural-sounding audio file will be generated within seconds. You can use voice synthesis up to 5,000 characters for free, so please give it a try.

Text-to-speech software "Ondoku" can read out 5000 characters every month with AI voice for free. You can easily download MP3s and commercial use is also possible. If you sign up for free, you can convert up to 5,000 characters per month for free from text to speech. Try Ondoku now.

HP: ondoku3.com
Email: ondoku3.com@gmail.com