Frequently asked questions
What is the base URL for the API?
The API base URL is https://api.1996wc.net/v1. You send POST requests to https://api.1996wc.net/v1/audio/speech to generate audio files. Other endpoints include GET /v1/voices and GET /v1/models for configuration details.
How do I authenticate with the API?
Include your API key in the request header as Authorization: Bearer tts-... . Each account holds one active key. You can issue a new key at any time, which immediately invalidates the previous one.
Which SDKs are compatible?
The request shape matches the OpenAI speech endpoint. Official OpenAI SDKs work by changing the base_url to https://api.1996wc.net/v1 and using your site-specific key. You can also use plain HTTP requests directly.
Can I stream audio in real-time?
No, we do not provide streaming or WebSocket support for real-time partial audio. You send text and receive the complete audio file in the response. Audio is generated and returned as a single unit.
Do you provide an official SDK?
We do not offer an official SDK of our own. You should use the OpenAI SDK or plain HTTP requests. There is no mobile SDK, WordPress plugin, or browser extension available for this API service.
How do I handle rate limits?
Limits are 60 requests per minute per key, or 10 per minute before your first top-up. Process requests sequentially. For longer texts, split input into parts of up to 4096 characters and join the resulting audio files.
What happens if the API is down?
We do not provide an SLA or uptime guarantee. If synthesis fails, the charge is returned in full. Requests are processed one after another, so under load, a request may wait in a queue before processing.
Can I use custom voices?
No, custom voice cloning is not offered. You must choose from eight preset voices like Aria, Nova, or Felix. Voices are based on licensed recordings and cannot be customized or cloned from your own audio samples.
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.mp3Python (openai)
from openai import OpenAI
client = OpenAI(base_url="https://api.1996wc.net/v1", api_key="tts-...")
with client.audio.speech.with_streaming_response.create(
model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
response.stream_to_file("hello.mp3")Node.js (openai)
import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({ baseURL: "https://api.1996wc.net/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));| voice | |
|---|---|
aria | female |
nova | female |
luna | female |
sage | female |
felix | male |
milo | male |
atlas | male |
orion | male |
| language | |
|---|---|
ar | العربية |
zh | 中文 |
da | Dansk |
nl | Nederlands |
en | English |
fi | Suomi |
fr | Français |
de | Deutsch |
el | Ελληνικά |
he | עברית |
hi | हिन्दी |
it | Italiano |
ja | 日本語 |
ko | 한국어 |
ms | Bahasa Melayu |
no | Norsk |
pl | Polski |
pt | Português |
ru | Русский |
es | Español |
sw | Kiswahili |
sv | Svenska |
tr | Türkçe |
Get Your API Key
Sign up for StoryWeave via Google or email to receive your API key. Google sign-ins include a $0.50 trial credit valid for seven days, while email accounts start with a zero balance. You can top up using USDT (TRC-20) to begin generating audio for your children's stories.
Sign Up Process
Visit the /get-api-key/ page to create an account. Authentication is handled directly through Google or standard email registration. Once registered, your unique API key is displayed immediately on the dashboard.
- Google Sign-In includes $0.50 trial credit
- Email accounts start with zero balance
- USDT (TRC-20) top-ups credited within minutes
Key Management
Each account holds one active API key visible on your dashboard. The key authenticates all requests sent to the /v1/ endpoints. Ensure you keep this key secure, as it links directly to your billing balance and usage statistics.
Key Revocation
You can issue a new API key at any time from your dashboard. When a new key is generated, the previous key becomes invalid immediately. This allows you to revoke access instantly if a key is compromised or no longer needed.
Make Your First Request
To generate your first audio file, send a POST request to the speech endpoint. You must include your API key in the Authorization header and specify the model, input text, and voice preset. The API returns a standard audio file directly in the response body.
This method works for short phrases or initial testing. For production use with OpenAI SDKs, configure the base URL to point to our API domain. Ensure your text does not exceed 4096 characters per request to avoid truncation.
Curl Example
Use this command to test the API. Replace YOUR_API_KEY with your actual key and adjust the text content.
The request sends a JSON payload containing the model, voice, input text, and optional parameters like response_format and speed. The response returns the audio data when synthesis is complete.
POST https://api.1996wc.net/v1/audio/speechAuthorization: Bearer YOUR_API_KEYContent-Type: application/json
JSON Body Structure
The request body requires specific fields. The model field accepts either tts-1 or tts-1-hd, which use the same engine and price. The input field contains your text, limited to 4096 characters. Spaces and punctuation count toward this limit.
You must specify a voice from the eight presets, such as aria for a clear narrator or nova for an upbeat tone. The response_format determines the output file type, defaulting to mp3. Optional fields include speed (0.25–4.0) and language (ISO code).
model: "tts-1" or "tts-1-hd"
Response Format
On success, the API returns the audio file in the requested format (mp3, wav, opus, flac, or pcm). The response headers include content-type information appropriate for the audio format. Failed requests return a JSON error object with details about the issue, such as invalid input or rate limits.
Integrate with OpenAI SDK
Use the official OpenAI Python or Node.js SDKs to integrate StoryWeave’s TTS API. The only change required is updating the base_url to https://api.1996wc.net/v1 while keeping the standard tts-1 or tts-1-hd model identifiers. This allows publishers to leverage familiar code structures without learning a new library.
Authentication works via your API key passed in the Authorization header. Since the request shape matches the OpenAI speech endpoint, you can swap the base URL in your existing configuration objects. This ensures immediate compatibility with standard SDK clients used for audio generation.
Base URL Configuration
Configure your SDK client to point to https://api.1996wc.net/v1. This single change redirects all speech requests to our infrastructure while maintaining the standard endpoint paths like /v1/audio/speech.
Ensure your API key is passed correctly. The SDK will handle the Authorization: Bearer header automatically if configured in the client settings.
- Base URL: https://api.1996wc.net/v1
- Standard endpoint: /v1/audio/speech
- Model: tts-1 or tts-1-hd
SDK Compatibility
The API accepts the exact same JSON body as the OpenAI Speech endpoint. Fields like input, voice, response_format, and speed work identically.
No custom wrappers are needed. Any SDK supporting the OpenAI TTS structure can connect directly to StoryWeave’s API by adjusting the origin URL.
Code Examples
Initialize the client with the new base URL and your tts-... key. Call the audio.speech.create() method with your text manuscript and desired voice preset like aria or nova.
The SDK returns the audio file when synthesis is complete. You can save it as MP3 or WAV for your publishing workflow. Note that failed requests incur no charge.
```python import openai client = openai.OpenAI( base_url="https://api.1996wc.net/v1", api_key="tts-your-api-key" ) speech = client.audio.speech.create( model="tts-1", voice="aria", input="Once upon a time, in a land far away...", response_format="mp3" ) speech.write_to_file("storybook_output.mp3") ```
Supported Audio Formats
Choose the audio format that best fits your distribution channel. MP3 offers small file sizes, while WAV provides uncompressed audio.
MP3 Compression
Select "mp3" for the most efficient storage and bandwidth usage. This format is optimal for web players and mobile apps where file size matters more than absolute fidelity.
WAV Quality
Use "wav" for lossless, uncompressed audio. This format preserves the full dynamic range of the synthetic voices, making it suitable for professional publishing workflows or direct integration into print-audio hybrid products.
FLAC and OPUS
FLAC provides lossless compression, offering smaller files than WAV without quality loss. OPUS is a supported format.
Voice Selection Parameters
Choose from eight distinct voice presets tailored for children's literature, ranging from the warm narrator Aria to the deep documentary tone of Orion. Each voice is designed to deliver clear, expressive audio that matches the mood of your manuscripts without requiring complex configuration.
Voice Presets
Select one of eight presets: Aria, Nova, Luna, and Sage for female voices; Felix, Milo, Atlas, and Orion for male voices. All voices support all 23 languages.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling
- Atlas: Neutral, news
- Orion: Deep, documentary
Speed Control
Adjust the speed parameter between 0.25 and 4.0 to match the pacing of your narrative. Slower speeds improve clarity for complex fairy tales, while faster speeds reduce production time for simpler stories.
Language Codes
Set the optional language field using ISO codes to ensure accurate pronunciation. While the system guesses Latin-script text as English, explicitly setting the language prevents errors for non-English texts.
- Supported: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish.
- Not supported: Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali and all others not in the list.

Rate Limits and Queues
Each API key is limited to 60 requests per minute. Before your first top-up, this limit drops to 10 requests per minute. Failed requests are free, but the text does not explicitly state they do not count against the rate limit.
Requests Per Minute
The rate limit applies per key, not per account. You have one active key at a time. If you issue a new key, the old one stops immediately. Plan your burst traffic accordingly.
- Standard limit: 60 requests/minute per key.
- Pre-top-up limit: 10 requests/minute.
- Limit is per key, not per account.
Queue Behavior
Requests are processed sequentially. If you exceed the limit, subsequent requests wait in a queue. Processing starts once slots free up. Short phrases may take a few seconds even when not queued.
Load Management
For long texts, split the manuscript into parts of up to 4096 characters. Join the resulting audio files after generation. This approach keeps individual requests within limits and avoids queue delays during high load.
Error Handling
Understanding error responses ensures your publishing pipeline remains stable. When synthesis fails, the API returns a clear JSON object detailing the issue, allowing your system to log the specific cause without crashing.
Common Errors
The most frequent error occurs when input exceeds the 4096-character limit. Other errors include invalid voice names or unsupported language codes. Failed requests are free, so you are not charged for these mistakes.
- Invalid request body
- Character limit exceeded
- Insufficient balance
Status Codes
The API uses standard HTTP status codes. A 200 OK indicates successful synthesis. Use 4xx codes for client errors like authentication failures or rate limits, and 5xx for server-side issues.
Retry Logic
Implement exponential backoff for temporary errors. Since requests are processed sequentially, a 429 Too Many Requests indicates you have hit the 60 requests per minute limit. Wait briefly before retrying.
Long Text Processing
Publishers often process manuscripts that exceed the single-request limit. You must split the input text into chunks of up to 4096 characters and join the resulting audio files.
This approach allows you to generate full-length children’s stories or fairy tales by manually splitting the text into chunks of up to 4096 characters.
Character Limits
Each API request accepts a maximum of 4,096 characters, including spaces and punctuation. If your manuscript is longer, you must split the input text into smaller parts before sending them to the endpoint.
Splitting Text
To process a long book, divide your text into chunks of up to 4,096 characters. You can use standard string splitting in your preferred language or library. Ensure each chunk is complete to avoid cutting off words mid-sentence, which preserves the natural flow of the narration.
Audio Joining
After receiving audio files for each chunk, concatenate them in order. Use any standard audio library to join the files into a single continuous audio book. This method ensures seamless playback across the entire manuscript.
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.
Sources and further reading
- Wikipedia
- ISO 639 language codes
- Creative Commons Attribution 4.0
- OpenAI API reference: create speech
- TRON developer hub: TRC-20
- openai-python on GitHub
- W3C WAI: making audio and video accessible
- LibriVox public-domain audiobooks
- openai-node on GitHub
- Tether (USDT)
- LibriTTS-R corpus (OpenSLR 141)
- LibriTTS-R paper (arXiv 2305.18802)
