About VoiceBloom: The Team Behind the TTS API

By VoiceBloom editorial team · Updated 2026-11-18

VoiceBloom is a text-to-speech API built for YouTube creators who want ethical voiceovers without hiring engineers. We offer eight preset voices derived from the LibriTTS-R dataset, which uses public-domain audiobook readings from LibriVox under CC BY 4.0. Each generated audio file includes an inaudible watermark identifying it as synthetic speech, ensuring transparency for your audience. This approach lets you produce clear audio while respecting the original source recordings.

We designed this tool for no-code users who value honesty. Here, you will find details on how our voices work, our data privacy practices, and our specific limitations. Whether you are using our preset voices or just exploring voice cloning concepts, this page explains the technology behind VoiceBloom so you can create content with confidence.

About VoiceBloom: The Team Behind the TTS API

Frequently asked questions

Who runs this site?

VoiceBloom is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, or other major brands. Our team focuses on providing a straightforward API for YouTube creators who need synthetic speech without complex engineering overhead or enterprise contracts.

How are the voices licensed?

Our voices use licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain LibriVox readings. Each generated file includes an inaudible watermark marking it as synthetic speech. This ensures ethical sourcing while giving you clear, usable audio files for your YouTube content without royalty disputes.

Is my data used for training?

No. Your input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata (time, characters, status) solely for billing. Your creative content remains private and yours.

How do I contact support?

Support is available by email only. We do not offer a phone number, live chat, or SLA. As an independent service, we do not provide 24/7 dedicated lines or enterprise-grade uptime guarantees. Please email us directly for any questions or issues regarding your account or API usage.

Do you offer custom voices?

We don’t offer custom voice cloning, voice design, or uploading your own voice. Instead, choose from eight preset voices like Aria, Nova, or Felix. These are based on licensed recordings and are ready to use immediately. If you need a unique voice, you will need to use our existing presets.

Is there an SLA?

No, we do not offer an SLA or uptime guarantee. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real time, but short phrases may take a few seconds. We provide the API; we do not guarantee specific availability windows.

What is the source of the voices?

Our eight voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These sources provide the base for our presets like Aria, Felix, and Luna. Each generated file includes an inaudible watermark to identify it as synthetic speech, ensuring transparency for your audience.

How do I revoke my API key?

You can issue a new API key at any time from the /get-api-key/ page. When you generate a new key, the old one stops working immediately, effectively revoking access for any application using the previous key. This allows you to quickly secure your account without needing to manage complex permissions or wait for a manual revocation process.

Who We Are

Sound wave illustration for: Who We Are

We are the developers behind VoiceBloom, building a straightforward TTS API for YouTube creators who want to clone voices ethically. We focus on delivering clear, usable audio assets without unnecessary complexity.

Editorial Team

Editorial Team

We are a small, focused group developing this API to serve the specific audio needs of video storytelling. Our team ensures the tool remains simple and direct for no-code users.

Mission Statement

Mission Statement

Our mission is to provide accessible, high-quality synthetic speech that respects original recordings. We aim to simplify the audio production workflow for independent creators.

Community Focus

We build for creators who value ethical voice usage. By using licensed recordings from LibriVox, we ensure our presets are grounded in public domain and CC BY 4.0 sources, giving you confidence in your video’s audio assets.

Our Voices and Licensing

Sound wave illustration for: Our Voices and Licensing

VoiceBloom’s eight preset voices are built on the LibriTTS-R dataset, providing a consistent and ethical foundation for your content creation needs.

This approach ensures that every voice model is grounded in verifiable data, allowing you to focus on your narrative without worrying about voice attribution complexities.

LibriTTS-R Source

Our voice presets are derived from the LibriTTS-R dataset, a large collection of spoken English recordings used for speech research.

This dataset provides the raw vocal data that defines the characteristics of our eight presets, ensuring a consistent baseline for all generated audio.

  • Dataset: LibriTTS-R

CC BY 4.0 License

The underlying audio data is licensed under Creative Commons Attribution 4.0 (CC BY 4.0).

This license allows for broad usage rights, giving you the freedom to incorporate generated audio into your YouTube videos and other projects.

Public Domain Recordings

Many of the source recordings originate from LibriVox, which offers public-domain audiobook readings.

Using these recordings helps us maintain a clear legal structure for the synthetic voices you use, ensuring that your content is based on freely available human speech.

image:

Our Voices and Licensing

Data Privacy Policy

Sound wave illustration for: Data Privacy Policy

We value your creative control and data integrity. Our API processes your text solely to generate the requested audio file, ensuring that your source material remains private and purpose-specific during synthesis.

Input Text Usage

Input text is used only to produce the audio and is not stored after the response is delivered. Once the synthesis is complete, the text payload is discarded, meaning it remains transient and tied strictly to that specific generation task.

Billing Metadata

We retain minimal request metadata—specifically timestamp, character count, and status—to calculate your usage accurately and process your USDT top-ups. This data is kept solely for billing transparency and to ensure fair rate-limit enforcement, with no personal identifiers attached.

No Training Data

Your input text is never used for training our models or improving the engine. The voices you use are based on licensed recordings from LibriTTS-R, but your specific submissions remain isolated and are not ingested into the training dataset.

Honest Limitations

Sound wave illustration for: Honest Limitations

We deliver reliable synthetic speech without the overhead of enterprise infrastructure. Our system processes requests sequentially, meaning longer texts generate at roughly real-time speed, while short phrases take a few seconds. Under load, requests may wait in a queue, so performance is not guaranteed to be instant during peak usage.

Our pricing is straightforward: $0.01 per 1,000 characters. Failed requests are free. We do not offer custom voice cloning, streaming audio, or SSML. You get consistent synthetic output based on licensed recordings, with no risk of unexpected artifacts, but also no guarantees on uptime or specific latency targets.

No Streaming

Our API returns complete audio files (mp3, wav, opus, flac, pcm) after synthesis is finished. We do not support WebSocket streams or real-time partial audio chunks. You must wait for the full file to be generated and returned in the response.

This design keeps infrastructure simple and costs predictable for YouTube creators who need ready-to-edit audio files rather than live streams.

No Custom Cloning

We provide eight preset voices based on licensed LibriTTS-R recordings and LibriVox public-domain readings. We do not offer custom voice cloning where you upload your own audio to create a new voice model. You cannot upload a voice sample to clone it for your specific content.

Every generated file carries an inaudible watermark marking it as synthetic speech. This ensures transparency without requiring complex licensing negotiations for each creator.

No SLA

We do not offer a Service Level Agreement, uptime guarantee, or enterprise contract. There is no on-premise option or data-center choice. Support is by email only, with no phone number or live chat.

For most YouTube creators and indie developers, this model provides sufficient reliability for daily usage without the need for complex contractual agreements. If you require guaranteed uptime for critical infrastructure, this API may not be the right fit.

Honest Limitations

Contact and Support

Sound wave illustration for: Contact and Support

VoiceBloom is built by a small editorial team of YouTube creators who understand the need for reliable narration. We support our community through direct, no-nonsense communication.

Our support structure is simple: we are here to help you get your videos made, without corporate layers or phone trees.

Email Support

All support is handled via email. There is no live chat, no phone number, and no ticketing system to navigate. Simply send your question to our support address.

We prefer email because it allows for detailed, threaded conversations that you can reference later. It’s the most reliable way for us to assist you with API keys, billing, or voice selection.

Response Times

We aim to respond as quickly as possible to all incoming messages. While we do not guarantee a specific turnaround time, you can expect a reply within a reasonable window during active hours.

If your query involves a billing issue or a technical error, we prioritize getting you unblocked so you can continue creating content without unnecessary delay.

Feedback Channel

Your experiences shape how we improve the API. If you notice a voice sounding off or a format issue, let us know. We read every message and use your insights to refine our preset voices.

This direct line is how we ensure our tool remains practical for creators who just want to paste text and get audio.

Contact and Support

Join Our Community

Sound wave illustration for: Join Our Community

VoiceBloom is built by a small editorial team that lives on YouTube. We test every preset voice against real script lengths to ensure our API fits your production schedule. Our focus is practical: helping creators scale narration without hiring engineers or waiting for voice actor availability.

Creator Updates

We share practical tips on using our eight preset voices for ethical narration. See how other creators split long scripts into 4096-character chunks to maintain consistent audio quality across entire video series.

  • Tips on splitting text for seamless audio generation
  • Examples of using preset voices in video workflows

Feature Requests

Tell us what you need for your editor. If you require a specific speed range or format for your workflow, let us know. We prioritize changes that directly benefit YouTube creators building with code or simple HTTP requests.

Stay Informed

Get the latest news on pricing, character limits, and new voice presets directly. Join our channel to see real-time usage tips and discover how to split long texts for seamless audio generation.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Create stunning videos with ease using our intuitive platform designed for creators.

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. curl documentation
  3. LibriTTS-R paper (arXiv 2305.18802)
  4. IETF RFC 7845: Ogg Opus
  5. MDN: Web Speech API
  6. LibriTTS-R corpus (OpenSLR 141)
  7. TRON developer hub: TRC-20
  8. Tether (USDT)
  9. ISO 639 language codes
  10. LibriVox public-domain audiobooks
  11. Node.js documentation
  12. Creative Commons Attribution 4.0

More on this site