Frequently asked questions
What is a text to voice reader API?
It is a cloud API where you send text and receive an audio file. The endpoint is POST https://api.1996wc.net/v1/audio/speech. It accepts JSON bodies similar to the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by changing the base URL. You specify the model, voice, and format to get synthesized speech for your manuscripts.
Which voice is best for fairy tales?
Luna is designed for soft, storytelling narration, making it ideal for fairy tales. Aria offers a warm, clear narrator style suitable for children's books. For a calmer, instructional tone, Sage is also effective. You can choose any of the eight presets, as all voices support all 23 languages, allowing you to match the mood of your specific story.
How does the pricing work per character?
The cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with charges returned in full if synthesis fails. There are no monthly plans, seats, or minimum spends, and your balance does not expire. You only pay for the characters you successfully generate.
What languages are supported for children's books?
We support 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. If the language is not set, it is guessed, so set it explicitly for non-English Latin-script text to ensure accuracy.
How long does it take to generate audio?
Typical speed is roughly real time on long texts (about 25 characters of text per second of generation); short phrases take a few seconds. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. For longer texts, split them into parts of up to 4096 characters and join the resulting audio files.
Can I use my own voice for the narrator?
No, custom voice cloning is not offered. You must choose from the eight preset voices based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. You cannot upload your own voice or design custom voices for your narrators within this API.
Do you support SSML for pronunciation?
No, SSML is not supported. The API does not offer phoneme dictionaries or custom pronunciation lexicons. You control pronunciation by spelling words as you want them spoken in the input text. There are no emotion tags or advanced markup options available for fine-tuning the audio output beyond the standard voice and speed parameters.
Is the audio streaming or a file download?
The audio is returned as a file download, not streaming. There is no WebSocket or real-time partial audio support. You send a request and receive the complete audio file in formats like mp3, wav, opus, flac, or pcm. The input text is used only to produce the audio and is not stored after generation.
How do I pay for the API services?
Payments are made via USDT on the TRON network (TRC-20) only. The minimum top-up is $5, and credits are added automatically within minutes. There are no cards, PayPal, subscriptions, or invoices with VAT. You can sign up with Google or email, and your balance does not expire. Support is by email only; there is no phone number or live chat.
Do spaces and punctuation count as characters?
Yes, spaces and punctuation count as characters for billing purposes. The price is $10 per 1 million characters, including all spaces and punctuation marks. This means your total cost is based on the exact length of the text string you send in the input field, regardless of whether it contains only words or also includes formatting.
What is the maximum text length per request?
The maximum input text length is 4096 characters per request. For longer manuscripts, you must split the text into parts of up to 4096 characters and generate audio for each part. You can then join the resulting audio files to create the complete book. This ensures efficient processing and adherence to the API's request limits.
Are failed requests charged?
No, failed requests are free. If synthesis fails, the charge is returned in full. You only pay for successful audio generations. This applies to all requests regardless of the reason for failure. You can monitor your usage and balance on the /get-api-key/ page to track successful and failed requests accurately.
Is there a free trial available?
Yes, signing in with Google gives you $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. You can top up your balance using USDT on the TRON network at any time. The trial allows you to test the API before committing to paid usage.
Do I need a developer to use this API?
While the API is designed for developers using JSON and HTTP, you can use the /get-api-key/ page to view your key, balance, and a ready curl example. The endpoint shape matches the OpenAI speech API, so standard SDKs work by changing the base URL. Basic programming knowledge helps, but the provided examples simplify integration for non-developers.
First request
curl
curl https://api.1996wc.net/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.mp3Turn Text Manuscripts into Audio Books
StoryWeave converts your children’s book manuscripts into high-quality audio files via a simple API. Send text up to 4,096 characters and receive an audio file; generation takes a few seconds for short phrases or roughly real-time for long texts.
Simple API Integration
Integrate with existing tools using standard HTTP requests. The API follows a familiar structure, allowing you to generate audio by sending a POST request with your text and preferred voice settings.
High-Quality Narration
Choose from eight distinct voice presets, including warm narrators like Aria or soft storytelling voices like Luna. Each voice is based on licensed recordings, ensuring clear and expressive audio suitable for young audiences.
Fast Generation Times
Audio is generated quickly, with typical speeds reaching roughly real-time for long texts. Short phrases may take a few seconds to process, ensuring efficient turnaround for your publishing schedule.
Choose the Perfect Narrator for Your Story
Selecting the right voice is crucial for engaging young listeners. Our eight preset voices cover the full spectrum of storytelling tones, ensuring your manuscripts sound natural and expressive without requiring complex audio engineering.
Each voice is derived from licensed recordings, providing a professional baseline for your children's books. You can match the narrator's personality to the story's mood, whether it’s a gentle bedtime tale or an adventurous chapter.
Use these presets to maintain consistency across your entire catalog.
Warm Narrator Voices
Use Aria for clear, warm narration that feels like a classic storybook reading. Her tone is gentle and inviting, perfect for fairy tales and gentle narratives aimed at younger children.
Nova offers a bright, upbeat energy suitable for lively adventures or educational content where enthusiasm helps maintain a child's attention span.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat energy
Upbeat and Energetic
Felix brings an energetic, promo-style voice ideal for promotional read-alouds or fast-paced action sequences in your stories.
Orion provides a deep, documentary-style tone that adds gravity and seriousness to historical tales or moral lessons, distinguishing them from lighter content.
- Felix: Energetic, promo-style
- Orion: Deep, documentary tone
Calm and Instructional
Luna’s soft voice is ideal for storytelling with a soothing rhythm, perfect for bedtime stories or calming narratives.
Sage delivers a calm, instructional tone that works well for educational children's books, guiding young readers through concepts with clarity and patience.
- Luna: Soft, storytelling rhythm
- Sage: Calm, instructional tone
Support for Global Audiences
StoryWeave supports 23 languages, including English, Spanish, French, German, Japanese, and Chinese, allowing you to reach global audiences with a single API integration. Each voice can speak any of these languages, ensuring consistent quality across your catalog.
Automatic language detection simplifies workflows for mixed-language manuscripts. If the language field is omitted, the system guesses the language from the script, defaulting to English for Latin text. For non-English Latin-script content, explicitly setting the language code ensures accuracy.
23 Supported Languages
The API supports Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.
Any voice preset can speak any supported language, giving you flexibility in casting narrators for diverse stories.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Automatic Language Detection
Set the language parameter to an ISO code for precise control. If omitted, the system infers the language from the script, defaulting to English for Latin text.
Explicitly setting the language ensures correct pronunciation for non-English Latin-script text, avoiding misinterpretation by the detection algorithm.
Consistent Voice Quality
All voices use the same underlying engine, ensuring uniform audio quality regardless of language or voice preset.
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks, maintaining a consistent, natural tone across all 23 languages.
Transparent and Fair Pricing
StoryWeave charges $0.01 per 1,000 characters, ensuring you only pay for the text you actually use. Each voice can speak any of the 23 supported languages, and spaces or punctuation count toward the total. This model allows publishers to scale audio book production without worrying about sudden cost spikes or hidden fees.
Pay Per Character
At $10 per million characters, the cost is predictable and low. You can estimate your budget by counting the characters in your manuscript, including spaces. Failed requests are free, so you never pay for errors.
- $0.01 per 1,000 characters
- Spaces and punctuation count
- Failed requests are free
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. You can top up your balance with USDT (TRC-20) whenever needed, with no expiration on your funds.
- No monthly plans
- No seats or minimums
- Balance does not expire
Free Failed Requests
If synthesis fails due to a technical issue, the charge is returned in full. This ensures you are never billed for audio that was not delivered.
Technical Specifications for Publishers
The API supports standard audio formats including MP3, WAV, Opus, FLAC, and PCM, ensuring compatibility with most publishing platforms and distribution channels. You can select the format that best balances file size and quality for your specific needs.
Speed control allows you to adjust the narration pace from 0.25x to 4.0x, letting you fine-tune the listening experience for different age groups. This flexibility ensures the audio matches the intended mood and clarity of your children's stories.
Standard Audio Formats
Choose from MP3, WAV, Opus, FLAC, or PCM to suit your distribution requirements.
All formats are generated directly from the API response, ready for immediate use.
Speed Control
Adjustable speed range from 0.25x to 4.0x allows precise pacing control.
Ideal for adapting content to younger listeners or creating dynamic story variations.
Character Limits
Each API request accepts up to 4,096 characters of input text.
Longer manuscripts can be split into multiple requests and joined seamlessly.

How It Works
To integrate audio narration into your children's book workflow, send a POST request to the /v1/audio/speech endpoint. Provide your text (up to 4,096 characters), select a voice from the eight presets, and specify the desired output format such as MP3 or WAV.
The API processes your request and returns the generated audio file directly in the response. Because requests are processed sequentially, longer texts may require splitting into smaller chunks and joining the resulting audio segments.
Send Text via API
Construct a JSON body containing your manuscript text, the chosen voice (e.g., aria or luna for storytelling), and your API key. Ensure the text does not exceed 4,096 characters per request; split longer passages to maintain consistent audio quality.
- Use POST https://api.1996wc.net/v1/audio/speech
- Include model (tts-1 or tts-1-hd), input text, voice, and response_format
- Pass Authorization: Bearer key in headers
Receive Audio File
The server returns the synthesized audio in your requested format (mp3, wav, opus, flac, or pcm). Failed requests incur no charge, ensuring you only pay for successful narrations. The audio file includes an inaudible watermark marking it as synthetic speech.
Download and Distribute
Save the returned audio file and integrate it into your digital distribution pipeline. Since input text is not stored, you retain full control over your content. Combine segments for longer stories to create complete audio books ready for your audience.
- Supports mp3, wav, opus, flac, and pcm
- No data retention for input text
- Ideal for digital book distribution
Why Publishers Choose This API
Publishers can scale audio production from a single title to a entire catalog without proportional increases in operational overhead. Requests are processed one after another, so under load a request may wait in a queue.
Cost Effective Scaling
Pricing is based strictly on character count at $0.01 per 1,000 characters, with no monthly base fees or tiered commitments. This model allows publishers to generate audio for new releases or backlist titles on demand, paying only for what is actually produced.
- Pay-per-use model eliminates wasted budget on unused capacity.
- No minimum spend or monthly subscription fees.
- Failed requests are refunded in full.
No Infrastructure Management
The cloud-based API manages all server maintenance, updates, and scaling automatically. Your team focuses on editing manuscripts and distributing audio rather than managing servers, storage, or processing queues.
Ethical Voice Licensing
All voice presets are derived from licensed recordings (LibriTTS-R, CC BY 4.0) and public-domain audiobook readings. This provides a clear foundation for commercial audio books.
- Based on LibriTTS-R (CC BY 4.0).
- Uses public-domain source material.
- Clear commercial usage rights.
Get Started Today
Start by creating a free account on the /get-api-key/ page using your Google credentials or email. This step establishes your billing profile. Accounts created with Google receive a trial credit of $0.50 (about 50,000 characters) valid for 7 days; email accounts start without trial credit.
Create Your Account
Visit the registration page and select your preferred sign-in method. Accounts are tied to this specific site, ensuring immediate access to your dashboard upon verification.
Get Your API Key
Once logged in, your unique API key is displayed on the dashboard. This key authenticates your requests to the endpoint. You can generate a new key at any time, which immediately invalidates the previous one for security.
- Key starts with 'tts-...'
- One active key per account
- Instant invalidation of old keys
Run Your First Request
Use the provided curl example to send a POST request to the speech endpoint. Include your model choice (tts-1 or tts-1-hd) and a voice preset like 'aria' for warm narration. The system returns an audio file directly in the response.
- POST to /v1/audio/speech
- Supports OpenAI SDKs
- Returns MP3, WAV, or OPUS
Frequently Asked Questions
Common questions about StoryWeave’s TTS API, covering voice selection, pricing, and technical constraints for children’s book publishers.
Voice Options
We offer eight distinct voices, ranging from warm narrators to energetic promo styles. Each voice supports all 23 listed languages without accent drift.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Pricing Model
Cost is $10 per 1 million characters. Failed requests incur no charge. No monthly fees or subscriptions.
Language Support
Supports 23 languages including English, Spanish, French, German, Japanese, and Arabic. Any voice can speak any supported language.
Technical Limits
Maximum input is 4,000 characters per request. Rate limit is 60 requests per minute. Split longer texts manually for best results.
Audio Formats
Choose between mp3, wav, opus, flac, or pcm. Standard formats ensure easy integration with existing publishing platforms.
Data Privacy
Input text is used only for generation and not for training. Audio files are returned in the response and not stored.
Speed Options
Adjust speed from 0.25x to 4.0x. Typical generation is roughly real-time for long texts.
Trial Availability
Google sign-ups receive $0.50 credit (approx. 50,000 characters) valid for 7 days. Email accounts start with zero balance.
Payment Methods
We accept USDT (TRC-20) on the TRON network. Minimum top-up is $5. Credits do not expire.
Character Counting
All characters count, including spaces and punctuation. Price is $0.01 per 1,000 characters.
Voice Cloning
We do not offer custom voice cloning or uploading of your own voice. Voices are based on licensed LibriTTS-R recordings.
SSML Support
SSML is not supported. Control pacing via the speed parameter only.
Streaming Audio
We do not support streaming or WebSocket audio. Audio is returned as a complete file after processing.
SDK Availability
We do not have an official SDK. Use the OpenAI SDK by changing the base URL, or use plain HTTP.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This ensures that the base audio data used to train the voice models is free from restrictive copyright claims.
23 languages
Any voice speaks any of these languages.
