Meet the Editorial Team Behind Our VocalShift

By StreamVoice editorial team · Updated 2026-11-19

This page explains how we licensed our voice models and exactly where your data goes. We built this API for VTubers and streamers who want consistent, expressive narration without writing code. You will find clear details on our LibriTTS-R licensing, our data privacy rules, and the honest limits of the product.

If you are integrating VocalShift into your no-code streaming workflow, this section clarifies our data policy and support channels. We focus on transparency, so you know exactly what you are getting: simple text-to-speech with no hidden fees or complex SDKs. Read on to understand our team, our data policy, and why we designed this tool for creators.

Meet the Editorial Team Behind Our VocalShift

Frequently asked questions

Who runs the VocalShift?

VocalShift 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 simple API for VTubers and streamers who need consistent narration without coding. We operate as a standalone service, managed entirely through our website and email support channels.

Where do the voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R, which uses readings from the LibriVox public-domain audiobook collection. Each voice, from Aria to Orion, is derived from these source recordings. This foundation ensures high-quality synthetic speech while maintaining clear origins for the audio data used in our TTS engine.

Are the voices licensed correctly?

Yes, our voices are based on LibriTTS-R, licensed under CC BY 4.0, and source readings from LibriVox public-domain audiobooks. We use these established sources to create our eight presets. This licensing structure supports our commercial offering while respecting the original creators and the public-domain nature of the underlying LibriVox recordings.

Is my input text used for training?

No. Your input text is used only to produce the audio file requested. We do not use your text for training our models or improving the API. This ensures your content remains private and is not repurposed for model development, providing a clear separation between your usage data and our training datasets.

Are the generated audio files stored?

No. Generated audio is returned in the response and is not stored on our servers after delivery. We retain only request metadata, such as time, character count, and status, for billing purposes. This minimal data retention ensures that your actual audio content is transient and not kept long-term on our infrastructure.

How is my data protected?

We retain request metadata for billing but do not store generated audio or input text long-term. We do not offer specific certifications like SOC 2 or HIPAA, nor do we provide an SLA. Data protection relies on our standard operational practices for API services, with support available via email for any queries.

Do you have a physical office?

We do not list a physical office location. As an independent API provider, we operate digitally. You can reach us via email for support. We do not offer phone support or live chat, so all communication is handled asynchronously through our contact page or direct email correspondence with our team.

Can I contact you by phone?

No, we do not have a phone number. Support is provided by email only. There is no live chat or phone support available. If you have questions about your API key, billing, or technical issues, please send an email to our support address, and we will respond as soon as possible.

How do I report a bug?

You can report bugs or issues by contacting us via email. We do not have a public community forum or dedicated bug tracker. Please include details about your request, such as the voice used and the text input, to help us diagnose the issue. We handle all support inquiries through our email channel.

Is there a community forum?

No, we do not have a community forum. We are a small independent storefront focused on providing a reliable API. All discussions and support are handled directly via email. You can find technical documentation and code examples on our docs page, but there is no public forum for user-to-user interaction.

Are the voices royalty-free?

Our voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. You can use the generated audio commercially, but you should verify specific usage rights for your commercial distribution needs.

Can I use the voices commercially?

Yes, you can use the generated audio files commercially. There are no restrictions on using the output for VTuber streams, videos, or other projects. We do not offer custom voice cloning, so you cannot clone specific celebrities, but the eight presets are available for any commercial use upon payment of the API fees.

How do I get support?

Support is available by email only. We do not offer phone support, live chat, or an SLA. You can contact us via the contact page on our website. For technical issues, please provide your API key and request details. We aim to assist all users efficiently through our email support channel.

What is your data retention policy?

We retain request metadata, including time, character count, and status, for billing purposes. Input text is used only for generation and is not stored. Generated audio is returned in the response and not stored. We do not keep long-term records of your audio content, ensuring minimal data retention for your privacy and security.

Our Editorial Team

Sound wave illustration for: Our Editorial Team

VocalShift is an independent storefront for a cloud text-to-speech API. We understand the pressure of maintaining consistent character voices across long streams without hiring a full voice cast.

Our approach is strictly creator-first. You can use the API with any tool that supports standard HTTP requests, such as OBS or Streamlabs, by generating audio from simple text inputs. We prioritize stability and ease of use over complex enterprise features, ensuring our tool fits naturally into your existing setup.

Who We Are

Who We Are

We are developers and content creators who started VocalShift to solve a specific problem: getting consistent, high-quality narration without coding expertise.

  • Built by VTubers for VTubers
  • No-code workflow experts
  • Active community members

Stream-Focused Approach

Stream-Focused Approach

We optimized our API for the unique needs of streamers. With support for 8 distinct voice presets and 23 languages, you can maintain character consistency across different segments. Our rate limits and pricing are designed to be predictable for daily streaming schedules.

Community Engagement

Community Engagement

We actively listen to feedback from streamers and VTubers to improve our voice models and API usability. You can report issues and share your workflow via email.

Voice Licensing Details

Sound wave illustration for: Voice Licensing Details

VocalShift’s voice models are built on the LibriTTS-R dataset, ensuring transparent origins for every vocal preset. We use licensed recordings from LibriVox public-domain audiobook readings, providing a clean legal foundation for your stream content.

All voices are derived from these verified sources, allowing creators to focus on narration without worrying about complex royalty structures. This approach keeps our pricing simple and predictable for VTuber workflows.

LibriTTS-R License

LibriTTS-R License

Our voices originate from the LibriTTS-R dataset, which aggregates high-quality English audiobook readings. This dataset serves as the raw material for our eight voice presets.

We utilize the underlying structure and audio characteristics from this dataset to train our synthesis models, maintaining a direct lineage to the original performers.

  • Dataset: LibriTTS-R
  • Source: LibriVox audiobooks
  • Quality: High-fidelity recordings

CC BY 4.0 Usage

The foundational audio data is released under the Creative Commons Attribution 4.0 International license. This allows us to process and adapt the recordings for commercial TTS use without restrictive royalties.

The CC BY 4.0 license ensures that the base material remains freely usable, supporting our no-code, creator-first model.

  • License: CC BY 4.0
  • Commercial use: Allowed
  • Royalties: None

Public Domain Sources

Many recordings in LibriVox are in the public domain, meaning copyright has expired or was waived by the volunteers. This reduces legal ambiguity for streamers and VTubers using these voices.

We verify the status of the source recordings to ensure that your generated audio is safe for monetization on platforms like Twitch and YouTube.

  • Source: Public domain recordings
  • Volunteer narrators
  • Safe for monetization

Data Privacy Policy

Sound wave illustration for: Data Privacy Policy

We use your input text solely to generate the requested audio file. It is not used to train our models or improve voice quality, ensuring your scripts remain private. Generated audio is returned directly in the response and is not stored on our servers after delivery. This means your unique narration styles and content are never archived for future use.

We retain minimal request metadata—specifically the timestamp, character count, and status—to accurately calculate your billing. This data is kept only as long as necessary for accounting and dispute resolution. No personal identifiers are linked to the audio content itself, keeping your creative output distinct from your account details.

Text Usage Policy

Input text is processed only for synthesis. It is not used for model training or voice improvement. Your scripts remain private and are not archived.

We do not analyze your text for advertising or marketing purposes. The generated audio is returned immediately and not stored after the response is sent.

Audio Storage

Generated audio files are not stored on our servers. Once the response is delivered, the audio is gone from our systems.

This ensures that your unique voice outputs are not accumulated in a database for future access or analysis by us.

Metadata Retention

We keep request metadata including time, character count, and status for billing purposes. This data is retained only as long as needed for accounting and dispute resolution.

No personal identifiers are linked to the audio content, keeping your creative output distinct from your account details.

Honest Product Limits

Sound wave illustration for: Honest Product Limits

VocalShift is designed for simplicity and reliability in no-code workflows, but it has specific limits you should know. We prioritize straightforward audio generation over complex, real-time pipelines, ensuring your stream stays stable without unnecessary technical debt.

Understanding what the API does not do helps you plan your automation correctly. We avoid over-promising on features that don’t exist, so you can integrate with confidence.

No Streaming Support

The API returns complete audio files (mp3, wav, opus, flac, or pcm). You receive the full synthesis result in one response.

No Custom Cloning

We do not offer custom voice cloning or the ability to upload your own voice samples. Our eight presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) are based on licensed recordings from LibriTTS-R and public-domain audiobook readings.

  • No voice design or emotion tags
  • No uploading personal voice data

Standard Features

We do not provide SSML, phoneme dictionaries, or custom pronunciation lexicons. There is no official SDK, mobile app, or WordPress plugin—just a standard HTTP API that works with any tool capable of sending JSON requests.

  • No streaming or WebSocket support
  • No SSML or phoneme control
Honest Product Limits

Contact Information

Sound wave illustration for: Contact Information

We don’t offer phone lines or live chat widgets. If you need help with your API key or billing, our only support channel is email. This keeps things simple and lets you send detailed context without waiting on hold.

Email Support Only

Send your questions to [email protected]. Please include your account email and a description of the issue. We avoid complex ticketing systems to keep communication direct and transparent for our no-code user base.

Response Time

We aim to reply within 24 hours on business days. Since we are a small, independent team, higher volumes may extend this slightly. We prioritize clear, actionable answers over speed.

Feedback Channel

Use the same email address for feature requests or bug reports. We read every message and regularly adjust our voice presets and pricing based on what VTubers and streamers tell us.

Why We Built This API

Sound wave illustration for: Why We Built This API

We built VocalShift because existing tools felt too complex for streamers who just want to talk. Our API is designed for consistency, letting you generate clear narration for your streams without wrestling with coding languages or heavy software installations.

Creator-First Design

Every voice preset, from Aria’s warm narration to Atlas’s neutral news tone, is available for your stream. We focus on delivering reliable audio that fits seamlessly into your content without distracting your audience with robotic artifacts or awkward pauses.

  • Voices based on licensed LibriTTS-R recordings
  • Inaudible watermarks mark synthetic speech
  • Optimized for clear stream narration

No-Code Friendly

Transparent Pricing

We charge $10 per million characters, ensuring you only pay for what you use. There are no hidden monthly fees or minimum spend requirements, and failed requests are free. You can top up with USDT on TRON, keeping your workflow simple and predictable.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Selecting the right voice ensures your content resonates with the intended audience, whether you are hyping a win or explaining a tutorial.

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. LibriTTS-R corpus (OpenSLR 141)
  3. TRON developer hub: TRC-20
  4. Python documentation
  5. curl documentation
  6. LibriTTS-R paper (arXiv 2305.18802)
  7. Node.js documentation
  8. OpenAI API reference: create speech
  9. Tether (USDT)
  10. W3C WAI: making audio and video accessible
  11. FFmpeg documentation
  12. LibriVox public-domain audiobooks

More on this site