Discover the Transparent Text-to-Speech Solution for Startups

By TaleTTS API editorial team · Updated 2026-11-18

This page explains how TaleTTS API works for startups building interactive children’s books and educational audio. You will learn about our independent infrastructure, the licensed voices behind our service, and exactly how we handle your data.

We built this API to help developers turn written stories into natural-sounding audio with a single API call. Unlike large platforms, we offer a straightforward pricing model and clear technical limits. Read on to understand our voice licensing, data policies, and how our email-only support fits your development workflow.

Discover the Transparent Text-to-Speech Solution for Startups

Frequently asked questions

Who owns the voices?

The voices are based on licensed recordings from LibriTTS-R, which uses public-domain audiobook readings from LibriVox. We do not own the original source material but have licensed it for use in our synthetic voice presets. The generated audio files are yours to use according to our pricing terms.

Are the voices copyrighted?

The source recordings come from LibriVox, which provides public-domain audiobook readings. The specific voice presets we offer are derived from these public-domain sources. Therefore, the underlying voice models are not subject to restrictive copyright, allowing flexible use in your applications without additional licensing fees.

How is my data used?

Input text is used solely to produce the audio file for your request. We do not use your input text for training our models or improving the service. Request metadata, such as time, character count, and status, is retained strictly for billing and usage tracking purposes.

Do you store my text?

No. Input text is processed to generate the audio response and is not stored after the request is completed. Only request metadata, including timestamp, character count, and status, is kept for billing verification. Your actual written content remains transient and is not archived.

Do you store the audio?

No. Generated audio is returned directly in the API response and is not stored on our servers after delivery. You receive the file immediately, and we do not keep a copy of the synthesized audio. This ensures your content remains private and under your control.

How do I contact support?

Support is available via email only. We do not offer phone support or live chat. You can reach our team through the contact page or by emailing us directly. Please include your account details and a description of your issue for faster resolution.

Is there a phone number?

No. We do not provide a phone number for customer support. All inquiries are handled via email to ensure efficient tracking and response. You can find our email address on the contact page. This approach allows us to manage support tickets systematically.

Do you have a live chat?

No. We do not offer live chat support. Communication is conducted exclusively through email. This allows for detailed explanations and attachment of relevant logs or screenshots. You can initiate a support request by emailing us at any time, and we will respond promptly.

What is the CC BY 4.0 license?

CC BY 4.0 is a Creative Commons Attribution license. Our voice presets are based on LibriTTS-R, which uses this license. It allows you to share and adapt the material for any purpose, even commercially, as long as you give appropriate credit to the original creators.

What is LibriVox?

LibriVox is a platform that provides public-domain audiobook readings. Our voice presets are derived from recordings available through LibriVox. These recordings are in the public domain, allowing us to use them as the foundation for our synthetic voice models without additional licensing constraints.

Are the voices synthetic?

Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. The voices are created by processing licensed recordings from LibriVox. While natural-sounding, they are algorithmically generated and not direct recordings of human speakers, ensuring consistent quality and availability.

Do I need to credit the API?

No specific attribution is required by our license terms for using the API. However, since the underlying voices come from public-domain sources via LibriVox, you may choose to credit them if desired. There is no mandatory requirement to display our brand name in your final product.

Can I use the API commercially?

Yes. You can use the generated audio for commercial purposes, including children's books, educational apps, and games. There are no restrictions on usage type. You pay for characters used, and the resulting audio files are yours to distribute commercially without additional royalty fees.

Is the API GDPR compliant?

We do not have a GDPR certificate. We process data within standard cloud environments. Input text is not stored, and audio is not retained. For specific legal requirements, review our data practices or contact us via email.

Do you have an SLA?

No. We do not offer a Service Level Agreement (SLA). There is no guaranteed uptime percentage or financial compensation for service interruptions. The API is provided as-is, and while we strive for reliability, we do not contractually guarantee specific performance metrics or availability.

What is your uptime guarantee?

We do not provide an uptime guarantee. There is no SLA to ensure a specific percentage of availability. Service may vary based on load. We aim for consistent performance, but no formal guarantee is offered, so plan your integrations accordingly without relying on strict uptime metrics.

Who we are

Sound wave illustration for: Who we are

TaleTTS API is an independent provider of cloud-based text-to-speech services, operating separately from major tech brands. We specialize in generating natural-sounding narration for startups creating interactive children’s books and educational audio content. The API turns written stories into audio with a single API call, allowing developers to integrate high-quality voiceovers without managing complex infrastructure.

Independent API provider

Independent API provider

We are not affiliated with OpenAI, Google, or Amazon. Our infrastructure is designed specifically for the narrative needs of indie developers, ensuring that our service remains focused and transparent.

Focus on storytelling

Focus on storytelling

Our eight voice presets—from warm narrators to energetic promo styles—are tuned for clarity and emotional resonance in children’s stories and educational materials. We prioritize natural intonation over generic robotic speech, making every generation suitable for reading aloud.

Startup-friendly approach

We offer a simple pricing model at $10 per million characters, with no monthly plans or hidden fees. Startups can begin with a $0.50 free trial via Google sign-in, or top up via USTRC-20. This approach removes financial friction, letting you scale your audio production as your user base grows.

  • No monthly plans or minimum spend
  • Simple per-character billing ($0.01/1000 chars)
  • Instant API key issuance
  • Support for 23 languages including English, Spanish, and German

Voice licensing

Sound wave illustration for: Voice licensing

Our voices are built on high-quality recordings from the LibriTTS-R dataset, derived from public-domain audiobook readings hosted by LibriVox. This foundation ensures a natural, human-like quality ideal for children's stories and educational content without the overhead of managing complex voice studios.

Each voice preset—from Aria’s warm narration to Orion’s deep documentary tone—is based on these licensed sources. By leveraging existing public-domain material, we provide consistent, reliable audio for your interactive books while keeping infrastructure costs low for early-stage startups.

LibriTTS-R recordings

All eight voice presets are generated from the LibriTTS-R dataset, which contains hours of clean, read-aloud English text. This dataset was originally collected for speech research, ensuring clear articulation perfect for educational audio and storytelling applications.

  • Derived from LibriVox public-domain audiobooks
  • Clean, read-aloud English text
  • Clear articulation for narration

CC BY 4.0 license

The underlying audio data is licensed under Creative Commons Attribution 4.0 International. You can use the generated audio in your applications.

  • Creative Commons Attribution 4.0
  • No additional licensing fees for end-users
  • Transparent source material

LibriVox public domain

The original recordings come from LibriVox, a volunteer-driven project creating free audio books. Since these works are in the public domain, we can offer voices without the legal complexity of negotiating individual rights for each voice actor.

  • Volunteer-driven project
  • Free audio books
  • Public domain status
Voice licensing

Data policy

Sound wave illustration for: Data policy

We process your input text exclusively to generate the requested audio file. The text is not used for training our models or improving the voice engine. Your content remains yours, ensuring confidentiality for your proprietary stories and educational materials.

Generated audio is returned directly in the response and is not stored on our servers after delivery. This minimizes data retention and ensures that your narrative assets are not archived indefinitely.

Billing metadata kept ['We retain request metadata—including timestamp, character count, and status—solely for accurate billing and troubleshooting. This data helps us verify that charges align with usage and resolve any discrepancies in your account.', 'No other personal or content data is preserved. Your focus remains on creating engaging content, while we handle the technical infrastructure transparently.', 'bullets']

Input text not trained ['Text is used only for synthesis.', 'Not used for model training.', 'Content remains confidential.']

No audio storage ['Audio returned in response.', 'Not stored on servers.', 'Minimizes retention risk.']

Technical limits

Sound wave illustration for: Technical limits

The API returns full audio files via standard HTTP responses, so real-time partial audio streaming is not available. Requests are processed sequentially; under load, synthesis may wait in a queue, taking a few seconds for short phrases or roughly real-time for long texts.

Each request supports up to 4096 characters of text. For longer stories, you must split the input into parts and join the resulting audio files on your end. This ensures reliable delivery without complex WebSocket management.

No streaming support

Synthesis happens asynchronously. You receive the complete audio file only after processing finishes. This design simplifies integration but means you cannot play audio while it is being generated.

No SSML support

The API uses plain text input. There is no support for Speech Synthesis Markup Language (SSML), phoneme dictionaries, or custom pronunciation lexicons. You control pacing and emphasis by adjusting the speed parameter or splitting text manually.

No voice cloning

Choose from eight preset voices based on licensed recordings. We do not offer custom voice cloning, uploading your own voice samples, or voice design. Each voice is a fixed preset available for all supported languages.

Technical limits

Contact and support

Sound wave illustration for: Contact and support

We keep our support structure simple and direct. All inquiries are handled via email, ensuring that every question receives a thoughtful, written response without the noise of live queues or automated menus. This approach allows our small team to focus on solving your specific technical or billing issues efficiently.

Email support only

Send your questions to our support address. We prioritize clarity and accuracy in our replies, so you can reference the exact details of your API key, usage, or integration challenge in your message.

No live chat

We do not offer real-time chat widgets. This eliminates the pressure of immediate response times and allows you to compose detailed technical queries without interruption. You can attach logs, code snippets, or error messages for a more accurate diagnosis.

No phone support

There is no phone number for customer service. By avoiding voice calls, we maintain a consistent, asynchronous workflow that respects your development time. You can reach out whenever it fits your schedule, and we will respond with a clear, documented solution.

Contact and support

Mission

Sound wave illustration for: Mission

We believe every story deserves a voice. By removing technical barriers, we enable creators to turn written text into natural-sounding narration with a single API call, making high-quality audio production accessible to any team.

Democratizing storytelling

Our mission is to simplify the process of creating audio content for children's books and educational materials. We provide a straightforward TTS API that integrates directly into your workflow, allowing startups to focus on narrative rather than infrastructure.

Supporting accessibility

We help developers create inclusive digital experiences by converting text into clear, natural speech. This ensures that stories and educational content are available to a wider audience, including those who benefit from audio formats.

Empowering developers

We give you the tools to build custom audio solutions without managing complex voice infrastructure. With simple endpoints and clear documentation, you can integrate high-quality voiceovers into apps and web platforms efficiently.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Craft enchanting digital fairy tales that ignite imaginations and inspire the next generation of dreamers.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. openai-python on GitHub
  3. Python documentation
  4. FFmpeg documentation
  5. LibriTTS-R corpus (OpenSLR 141)
  6. LibriVox public-domain audiobooks
  7. Node.js documentation
  8. W3C WAI: making audio and video accessible
  9. TRON developer hub: TRC-20
  10. curl documentation
  11. IETF RFC 7845: Ogg Opus
  12. MDN: Web Speech API

More on this site