Frequently asked questions
Who runs this website?
StoryWeave is an independent storefront for a cloud text-to-speech API. This site operates separately from other brands and manages its own accounts. Each site in the network is independent, meaning your account and API key are specific to 1996wc.net. We provide the infrastructure for publishers to convert text manuscripts into audio files efficiently.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint follows the same request shape as the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by changing the base URL. However, we are a separate entity with our own pricing, voices, and infrastructure, distinct from OpenAI’s services.
How are the voices licensed?
Our eight voice presets are based on licensed recordings from LibriTTS-R, which is available under the CC BY 4.0 license. These recordings originate from LibriVox public-domain audiobook readings. This foundation ensures high-quality, natural-sounding synthetic speech suitable for children’s stories and fairy tales without requiring complex voice design.
Is my text data used for training?
No, your input text is used only to produce the audio file and is not used for training models. The generated audio is returned in the response and not stored. We retain request metadata, such as time and character count, strictly for billing purposes to ensure accurate invoicing.
How can I contact support?
Support is available by email only. We do not offer a phone number, live chat, or an SLA. You can reach us via the contact page or the email address provided in your account dashboard. We respond to inquiries directly, ensuring you get assistance with your API integration or billing questions.
Do you have a physical office?
We do not list a physical office address. As an independent API provider, we operate digitally. Our infrastructure is cloud-based, allowing you to send text and receive audio files globally. All interactions, including sign-ups, top-ups, and support, are managed through our website and email communication channels.
What is the CC BY 4.0 license?
CC BY 4.0 is a Creative Commons license that allows others to distribute, remix, adapt, and build upon the licensed work, as long as they credit the original creators. Our voices use recordings from LibriTTS-R under this license. This ensures the underlying audio data is legally sourced and clear for commercial use in your projects.
Can I request a new voice?
We do not offer custom voice cloning or voice design for customers. You cannot upload your own voice or request new specific presets. You must choose from the eight available voices: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These cover various tones suitable for narrating children’s stories.
Who We Are
StoryWeave is an independent storefront for a text-to-speech API, designed specifically for publishers of children's stories and fairy tales. We provide a practical, step-by-step workflow to generate clear, expressive audio books from text manuscripts quickly and affordably.
Editorial Team
Our editorial team focuses on the specific needs of children's literature publishers. We prioritize clear narration and expressive pacing that suits fairy tales, ensuring the audio output matches the tone of your manuscripts without unnecessary complexity.
Independent Storefront
We operate as an independent storefront for the same text-to-speech API. You receive a single API key for up to 60 requests per minute, simplifying integration for your production pipeline.
Mission
Our mission is to make professional-quality audio books accessible to publishers of all sizes. We aim to remove the technical barriers to audio production, allowing you to focus on the stories while we handle the synthesis.
Voice Licensing
StoryWeave’s voice library is built on the LibriTTS-R dataset, providing eight distinct presets for children's literature. These voices are derived from public domain audiobook readings, ensuring a consistent and high-quality audio foundation for your manuscripts.
Each voice is carefully selected to match the tone of fairy tales and stories, from warm narrators to energetic storytellers.
The audio files generated carry an inaudible watermark to identify them as synthetic speech, maintaining transparency for your publishers.
LibriTTS-R Source
All voice models in our API are based on the LibriTTS-R dataset. This collection provides the raw audio material used to create our voice presets.
The dataset includes a wide range of English speakers, allowing us to create distinct presets like Aria, Nova, and Felix that suit different narrative styles.
- Based on LibriTTS-R dataset
- Eight distinct voice presets
- Engineered for clear narration
CC BY 4.0 License
The underlying voice recordings are licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). This allows us to use these recordings to build our commercial API while respecting the original creators' rights.
The underlying voice recordings are licensed under Creative Commons Attribution 4.0 International (CC BY 4.0).
Public Domain Readings
Many of the source recordings come from LibriVox, a community of volunteers reading public domain books. This means the underlying performances are free of restrictive copyright claims.
We enhance these recordings with modern processing to ensure consistent quality and speed, making them ideal for publishing children's stories.
Data Privacy Policy
StoryWeave processes your text manuscripts solely to generate the requested audio files. Once the synthesis is complete, the generated audio is returned in the response and is not stored on our servers for later retrieval.
Input Text Usage
Your input text is used exclusively for the immediate production of the audio file. We do not retain copies of your manuscript after the audio has been delivered to your API client.
No Training Data
The text you submit for synthesis is not used to train our models or improve the TTS engine. Your content remains yours, separate from our training datasets.
Metadata Retention
We retain request metadata, including timestamp, character count, and status, strictly for billing and account management purposes. This data ensures accurate charge calculation for your usage.
Technical Limitations
StoryWeave delivers complete audio files via standard HTTP responses. You receive the final synthesis result, not partial chunks as they generate. This simplifies integration for batch processing.
Our API accepts plain text inputs up to 4096 characters. It does not process SSML markup tags for fine-grained control over pauses, emphasis, or pronunciation. If you need precise timing adjustments, you must pre-segment your text into smaller requests or adjust the global speed parameter.
No Streaming
We return the final audio file in the response body. There is no WebSocket connection or Server-Sent Events stream for partial audio chunks. This approach ensures reliable delivery for your children's story manuscripts without managing complex streaming state.
No SSML
The API does not interpret SSML tags. You cannot insert custom breaks or emphasize specific words via markup. Control is limited to the speed parameter (0.25–4.0) and voice selection. For precise pacing, split your text into smaller segments.
No Custom Cloning
We do not offer voice cloning or custom voice design. You choose from eight licensed presets based on LibriTTS-R recordings. These voices are fixed and cannot be trained on your specific text or style, ensuring consistent, predictable output for your publishers.
All voices are based on licensed recordings from LibriVox public-domain audiobook readings, available under CC BY 4.0. You cannot upload a sample voice to create a unique clone.

Contact and Support
We provide a single email address for all technical and billing inquiries. There is no phone number, live chat, or ticketing system. You can find our contact details on our /contact/ page or in the footer of every page.
Email Support
Send your message to [email protected]. Include your account email, the issue description, and any relevant request IDs from your dashboard. For billing questions, specify the transaction date and amount.
No Phone Number
We do not offer phone support. This keeps our operations lean and affordable for publishers. All communications are asynchronous, allowing you to include logs and context without waiting on hold.
Response Times
Complex technical issues may take longer. We do not guarantee specific response times or offer priority support tiers.
- Standard response: within 24 hours on business days
Not Affiliated With
StoryWeave operates as an independent storefront for a single text-to-speech API, distinct from the companies often associated with similar technology. We do not use OpenAI’s infrastructure, nor are we owned by or partnered with major tech providers. We do not use their models, servers, or billing systems.
OpenAI
Our API endpoint and SDK compatibility mimic the OpenAI speech format, but we are not OpenAI. We do not use their models, servers, or billing systems. The similarity allows you to use the official OpenAI SDK with our service, but the underlying engine and voice presets are ours.
- Independent infrastructure
- Separate billing and keys
- Different voice models
ElevenLabs
We are not ElevenLabs. Our voices are licensed from LibriTTS-R and LibriVox, whereas ElevenLabs uses different sources and training methods. We do not offer their specific cloning features or multi-language voice presets. Our pricing and character limits are set independently.
- Different voice source
- No custom cloning
- Independent pricing
Other Brands
We are not affiliated with Google, Amazon, Microsoft, or any other cloud provider. We do not resell their services. All text processing happens on our own servers. Comparisons with other brands are based on published facts and do not imply partnership or endorsement.
- No brand affiliation
- Independent operations
- Factual comparisons only
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.
