Frequently asked questions
What is a Japanese text reader API?
It is a cloud service that converts text into audio files via a simple API call. You send text to the endpoint and receive an audio file, such as MP3 or WAV. This allows teachers to quickly generate audio for lesson materials without manual recording, ensuring consistent delivery for students.
How does the API handle Japanese pronunciation?
The API uses eight preset voices that can speak Japanese naturally. You can specify the language code to ensure correct pronunciation, though the system also guesses language from the script. The voices are based on licensed recordings, providing clear and accurate speech for educational content without needing custom pronunciation dictionaries.
Which voices are best for storytelling?
For storytelling, Luna is ideal for soft, narrative styles, while Aria offers a warm, clear narrator tone. Sage provides a calm, instructional voice suitable for guided reading. These female voices deliver clear audio that helps maintain student engagement during lessons or accessibility readings without requiring complex setup.
Can I use the API for classroom accessibility?
Yes, the API supports multiple languages including Japanese, making it suitable for diverse classrooms. You can generate audio files for texts up to 4096 characters, helping students with reading difficulties access content. The service is straightforward to integrate, allowing teachers to provide audio versions of lesson materials easily.
What languages does the API support besides Japanese?
The API supports 23 languages, including Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages, allowing for versatile educational content creation across different linguistic groups.
How much does it cost to read a 1000-character text?
The cost is $0.01 per 1,000 characters. Pricing is $10 per million characters, with spaces and punctuation counting toward the total. This flat rate ensures predictable costs for generating audio files, making it easy for teachers to budget for classroom resources without hidden fees or subscription requirements.
Is there a free trial available for teachers?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without this trial credit. This allows teachers to test the API’s quality and integration before committing to USDT top-ups for larger projects.
How do I pay using USDT?
Payments are made via USDT on the TRON network (TRC-20). The minimum top-up amount is $5, and credits are added automatically within minutes of transfer. There are no subscriptions or invoices; the balance does not expire. This method allows for direct, low-friction funding of your API usage account.
Can I change the speed of the audio for listening exercises?
Yes, you can adjust the speed between 0.25 and 4.0. This feature allows teachers to create listening exercises with varying difficulty levels. Slower speeds help students with processing difficulties, while faster speeds challenge advanced learners. The speed parameter is included in the JSON request body for easy integration.
Does the API support SSML for custom pronunciation?
No, the API does not support SSML. It uses eight preset voices with standard pronunciation based on licensed recordings. If you need custom pronunciation, you must adjust the input text directly. This keeps the integration simple, relying on standard text input rather than complex markup structures for audio generation.
How long does it take to generate audio?
Generation takes roughly real-time for long texts, about 25 characters per second. Short phrases may take a few seconds. Requests are processed sequentially, so under load, you might experience slight delays. This predictable timing helps teachers plan their lesson workflows and manage student expectations for audio delivery.
Is the audio stored after generation?
No, generated audio is returned in the response and not stored by the service. Input text is used only to produce the audio and is not used for training. Request metadata like time and status is kept for billing purposes. This ensures privacy for your classroom content and student data.
Can I use the OpenAI SDK with this API?
Yes, the API uses the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDK by changing the base URL to https://api.cb125.info/v1 and using your API key. This allows for easy integration with existing codebases and tools that already support OpenAI-style TTS endpoints.
What happens if a request fails?
If synthesis fails, the charge is returned in full. Failed requests are free, ensuring you only pay for successful audio generation. This protects your budget during testing or if temporary issues occur. You can retry requests without worrying about double-charging, making the API reliable for critical lesson materials.
First request
curl
curl https://api.cb125.info/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Why Teachers Choose Our API
The API handles Japanese text, ensuring pronunciation for classroom materials. By allowing teachers to set the language explicitly, the system avoids guessing errors common with mixed scripts, delivering clear audio for lesson planning and student listening exercises.
Accurate Japanese Pronunciation
Our engine correctly processes Japanese characters, reducing mispronunciations that disrupt student comprehension. You can specify the language code to ensure consistent output, even when mixing Latin and Japanese text in a single request.
- Explicit language code support prevents guessing errors
- Consistent pronunciation for lesson materials
Clear Voice Options for Narration
Choose from eight preset voices. Luna’s soft storytelling tone works well for fairy tales, while Sage’s calm instructional voice suits direct teaching. These options help maintain student engagement without auditory fatigue.
- Luna: Soft, storytelling tone for narratives
- Sage: Calm, instructional voice for lessons
Support for Accessibility Needs
Generate audio files in MP3, WAV, or FLAC formats to support diverse assistive technologies. The API provides reliable, synthetic speech for students who benefit from auditory learning or need text read aloud for accessibility compliance.
- Multiple audio formats for accessibility tools
- Reliable synthetic speech for auditory learning
Voices for Every Story Type
FableSays offers distinct voice presets tailored for educational narration, ensuring clarity and engagement in Japanese text-to-speech output. Teachers can select voices that match the tone of their lesson plans, from gentle storytelling to structured instruction.
Luna: Soft Storytelling Voice
Luna provides a soft, storytelling tone.
- Best for: Fairy tales, bedtime stories, narrative reading
Sage: Calm Instructional Voice
Sage delivers a calm, instructional tone suitable for explanatory texts, vocabulary drills, or structured lesson content.
- Best for: Lesson plans, instructional guides, vocabulary practice
Aria: Warm Narrator Voice
Aria offers a warm, clear narrator voice. Her balanced tone supports accessibility needs and ensures comfortable listening for extended reading sessions.
- Best for: General reading, accessibility support, mixed content
Languages and Formats
Teachers need precise pronunciation for Japanese lessons, which our API handles by detecting the script or allowing explicit language codes. The system supports 23 languages.
23 Supported Languages
Select from Japanese, English, Chinese, Korean, and 20 other languages. Any voice can speak any supported language, making it easy to create multilingual stories or support students learning different tongues.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
MP3, WAV, FLAC Audio Formats
Download audio in MP3 for web players, WAV for high-quality editing, or FLAC for lossless storage.
- MP3
- WAV
- OPUS
- FLAC
- PCM
Speed Control for Listening Practice
Adjust speech speed from 0.25x to 4.0x. Slower speeds help students catch individual phonemes, while normal speed mimics natural conversation, allowing you to tailor content to different proficiency levels.
Simple Integration for Educators
Integrating FableSays into your lesson workflow requires minimal coding effort. The API follows the standard OpenAI speech endpoint structure, allowing you to use familiar libraries and tools without learning a new proprietary format.
OpenAI SDK Compatible
Use the official OpenAI SDKs by simply changing the base URL to https://api.cb125.info/v1. Pass your API key via the Authorization header, and the request shape remains identical to what you already know. This reduces the learning curve for teachers who have already experimented with basic API calls.
- Drop-in replacement for standard TTS endpoints
- Uses standard JSON request bodies
- Compatible with Python, JavaScript, and other OpenAI SDK versions
Easy CURL Requests
For quick testing, send a POST request to /v1/audio/speech with your text, voice, and format parameters. The API returns the audio file directly in the response, allowing you to save it immediately for classroom use.
- Simple POST endpoint structure
- Immediate audio file return
- Easy to debug with standard command-line tools
No Custom SDK Required
You do not need to install or maintain a separate FableSays-specific software development kit. Standard HTTP clients and widely used OpenAI libraries handle all communication. This simplicity means fewer dependencies to update and less potential for compatibility issues in school IT environments.
Pricing for Schools and Tutors
For schools and tutors, FableSays offers a straightforward pricing model that scales with your usage. At $0.01 per 1,000 characters, costs remain predictable whether you are generating short exercises or full fairy tales. Failed requests are free, so you only pay for successful audio generation.
$0.01 per 1,000 Characters
Each character, including spaces and punctuation, counts toward your usage. This means a 4096-character request costs $0.04. You can monitor your balance and character consumption directly on your dashboard.
- Spaces and punctuation count as characters
- Failed requests are refunded in full
- Balance does not expire
No Monthly Fees or Subscriptions
You do not need a fixed plan or minimum spend. Whether you generate audio for one lesson or a entire semester, you only pay for what you use. There are no seats to manage and no recurring charges if you are not active.
Pay with USDT (TRC-20)
We accept USDT on the TRON network (TRC-20) for top-ups. The minimum deposit is $5, and credits appear in your account within minutes. No credit cards, PayPal, or VAT invoices are involved.
- USDT on TRON network (TRC-20) only
- Minimum top-up: $5
- Credited automatically within minutes

Technical Specifications
The API accepts input text up to 4096 characters per request. This limit ensures consistent processing speed and reliable audio generation for individual lesson segments or story chapters.
Generation speed is approximately real-time, producing about 25 characters of text per second of audio. Short phrases may take a few seconds to process, while longer texts generate continuously.
4096 Character Limit per Request
Each API call processes a maximum of 4096 characters. This constraint applies to all models, including tts-1 and tts-1-hd.
The character count includes spaces and punctuation. Exceeding this limit requires splitting the text before sending the request.
- Maximum 4096 characters per POST request
- Spaces and punctuation count toward the limit
- Applies to both tts-1 and tts-1-hd models
Real-Time Audio Generation
Audio synthesis typically completes in near real-time for standard-length inputs. Under load, requests may queue and wait for processing.
Failed requests do not consume your character balance, ensuring you only pay for successful audio generation.
- Processing speed: ~25 characters per second
- Requests are processed sequentially
- Failed requests are free
Automatic Text Splitting
For texts exceeding 4096 characters, split the input into smaller parts. Generate audio for each part separately.
Join the resulting audio files to create a continuous playback experience for students. This method maintains audio quality and avoids truncation.
- Split text into 4096-character chunks
- Generate audio for each chunk
- Join files for continuous playback
Data Privacy and Usage
Your input text is processed solely to generate the audio response and is not retained in the generated files. We ensure that the voice synthesis engine treats each request as a transient operation, delivering the audio file directly to your application without storing the raw text for long-term access.
Text Used Only for Generation
The text you send via the API is used exclusively for the immediate creation of the audio file. Once the synthesis is complete and the audio is returned, the input text is not stored for later retrieval or display.
No Training on Input Data
We do not use your submitted texts to train or improve our underlying voice models. Your stories and lesson materials remain distinct from the data used to shape the AI's voice characteristics, ensuring your content privacy is maintained separately from model development.
Metadata Kept for Billing
To ensure accurate charging, we retain request metadata including the timestamp, character count, and status of each synthesis job. This data is used strictly to calculate your usage based on the $0.01 per 1,000 characters rate and to verify that failed requests are credited back to your balance.
Common Use Cases
Teachers and methodologists use FableSays to transform static text into engaging audio for classroom use. By converting children’s stories and lesson materials into speech, educators can provide consistent reading models that support both literacy development and accessibility needs without requiring voice acting skills.
Reading Fairy Tales Aloud
Use the Luna or Aria voice presets to narrate classic Japanese and international fairy tales. The API handles the 4096-character limit by splitting longer stories, allowing you to generate complete audio chapters for digital libraries or classroom listening stations.
- Generate full story readings from text inputs
Creating Audio Lessons
Methodologists can quickly turn lesson plans into audio formats for students who prefer listening. The Sage voice provides a calm, instructional tone ideal for explaining concepts, while the speed control (0.25–4.0) helps adjust pacing for different comprehension levels.
- Convert lesson plans to audio in minutes
Supporting Dyslexic Students
Audio support reduces the cognitive load of decoding text for students with dyslexia. By providing clear, synthetic speech that matches the curriculum text, teachers offer an inclusive alternative that allows students to focus on comprehension rather than reading mechanics.
- Accessible audio for diverse learning needs
Get Started Today
Start by signing up at /get-api-key/ to receive $0.50 in free trial credit. This gives you about 50,000 characters to test voice quality and integration without any financial commitment.
Once registered, generate your unique API key from your account dashboard. You can issue a new key at any time, instantly invalidating the previous one for security.
Sign Up for Free Trial
Visit /get-api-key/ and sign in with Google to receive $0.50 in credit. This trial is valid for 7 days and allows you to test all features, including longer stories, before paying.
Generate Your API Key
Navigate to your account settings to generate your API key. Use this key in the Authorization: Bearer header for all requests. You can rotate keys instantly if needed.
- Keys are unique to your account
- Old keys stop immediately upon rotation
- No expiration or monthly fees
Try the Demo Code
Use the OpenAI SDK or a simple curl command to send text. Point your base_url to https://api.cb125.info/v1. Replace tts-1 with your generated key to receive audio files.
- Send text via JSON body
- Receive MP3, WAV, or OPUS files
- Supports 23 languages including Japanese
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. It works well for young adult fiction or modern stories where a traditional fairy tale voice might feel too juvenile.
23 languages
Any voice speaks any of these languages.
