Independent TTS API: Voices, Pricing & Data Policy

By VocalGuide editorial team · Updated 2026-11-19

VocalGuide is an independent storefront for a text-to-speech API, tailored for HR agencies and corporate training teams. This page details our editorial mission, voice licensing from LibriTTS-R, and our strict data policy. We provide clear, factual information without hype, helping you understand exactly how our synthetic voices integrate into your e-learning workflows.

We cover our technical infrastructure, support channels, and contact details. We do not offer phone support or live chat. As an independent provider, we offer consistent, multilingual voiceovers that replace expensive studio recordings. Read on to learn about our data retention practices, our email-only support model, and how to reach our editorial and API teams for specific inquiries.

Independent TTS API: Voices, Pricing & Data Policy

Frequently asked questions

Who owns the voices used in the API?

Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Each generated file includes an inaudible watermark identifying it as synthetic speech. We do not offer custom voice cloning or upload your own voice for training.

Is the input text used for training models?

No. Input text is used solely to produce the specific audio file returned in the response. We do not use your input text for training our models. Only request metadata, such as time, character count, and status, is retained for billing purposes.

Can I use the generated audio commercially?

Yes. The voices are based on CC BY 4.0 licensed recordings from LibriVox public-domain readings. You can use the generated synthetic audio for your corporate training modules, e-learning, or other commercial projects.

How do I contact support?

Support is available by email only. We do not offer a phone number, live chat, or SLA. You can reach us via the contact form on our /contact/ page or through the details provided in your account dashboard.

Is there a Service Level Agreement (SLA)?

No, we do not provide an SLA or uptime guarantee. Requests are processed sequentially, so under load, synthesis may wait in a queue. We aim for reliable service but do not contractually guarantee specific availability or performance metrics.

Are there any certifications like SOC 2 or HIPAA?

No. We do not hold SOC 2, HIPAA, or GDPR certifications. Our infrastructure is designed for standard API usage. Input data is not stored long-term, reducing privacy risks.

Do you have a phone number?

No, we do not have a phone number. All support is handled via email. We do not offer live chat or direct voice support. Please use the /contact/ page to send your inquiries to our support team.

Is this site affiliated with OpenAI?

No. VocalGuide is an independent storefront for its own TTS API. While our endpoint shape matches the OpenAI speech endpoint for SDK compatibility, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft.

Our editorial mission

Sound wave illustration for: Our editorial mission

VocalGuide operates as an independent storefront for a single text-to-speech API, designed for HR and corporate training teams. We provide straightforward access to synthetic voices without the marketing noise of larger platforms.

Our goal is clarity. We focus on what the API actually does—generating audio from text—rather than promising features it does not have.

Honest comparisons

Honest comparisons

We compare VocalGuide against other TTS options using only published facts. For example, we note that our voices are based on recordings from LibriTTS-R and LibriVox. We avoid claiming superiority unless supported by data.

Fact-based guides

Fact-based guides

Our documentation details exact limits: 4,096 characters per request, 60 requests per minute, and specific pricing at $10 per million characters. We explain how to split long texts and why speed varies based on queue load.

No hype marketing

No hype marketing

We do not use superlatives like 'best' or 'most realistic.' We do not promise SLAs, uptime guarantees, or voice cloning. If a feature like SSML is missing, we state it plainly. Our tone is editorial, not promotional.

Voice licensing

Sound wave illustration for: Voice licensing

VocalGuide’s eight voice presets are built from licensed recordings, ensuring a transparent lineage for every synthetic audio file generated through our API. We do not manufacture these voices in isolation; instead, we derive them from established, high-quality datasets that have already undergone rigorous vetting processes.

LibriTTS-R source

LibriTTS-R source

All our voices originate from the LibriTTS-R dataset. This source provides a consistent acoustic foundation, ensuring that the warm narrator quality of aria or the deep documentary tone of orion remains stable across different languages and speeds.

CC BY 4.0 license

The underlying audio data is released under the Creative Commons Attribution 4.0 International license. This allows us to legally process and synthesize these recordings into our TTS models, providing a clear legal chain for corporate training modules.

Public domain recordings

The base recordings are sourced from LibriVox public-domain audiobook readings. This means the original vocal performances are free from copyright claims, allowing us to focus on engine performance rather than navigating complex royalty structures for each generated audio file.

Data policy

Sound wave illustration for: Data policy

VocalGuide operates as an independent storefront, meaning our data handling is distinct from the larger platforms we often compare against. We prioritize clarity for HR and corporate training teams who need to understand exactly where their content goes during the synthesis process.

Text not trained on

When you send text to generate audio, that input is used solely for the immediate synthesis of the audio file. We do not use your input text to train or improve our underlying models. Your curriculum content remains yours, with no risk of it becoming part of our training dataset.

No audio storage

Generated audio files are returned directly in the API response and are not stored on our servers after delivery. This ensures that your final voiceovers remain in your own infrastructure, reducing data retention risks for sensitive corporate training materials.

Metadata retention

We retain request metadata—specifically the timestamp, character count, and status—for billing and troubleshooting purposes. This minimal data allows us to process your USDT top-ups and resolve any synthesis issues, but it does not include the content of your audio or text.

Technical infrastructure

Sound wave illustration for: Technical infrastructure

VocalGuide operates as a fully cloud-based REST API, designed for seamless integration into existing HR and e-learning workflows. There is no on-premise deployment option; all synthesis occurs on our servers, ensuring consistent performance without local hardware requirements.

The API exposes standard endpoints compatible with existing developer tools. This architecture supports scalable usage for corporate training modules without requiring specialized infrastructure or dedicated servers on the client side.

Cloud-based API

Our service is hosted entirely in the cloud, accessible via standard HTTP requests. This eliminates the need for local processing power, allowing HR teams to generate voiceovers for e-learning modules on demand, regardless of their internal IT setup.

The cloud model ensures that voice engine updates and improvements are deployed automatically, keeping your audio quality consistent across all generated content without manual intervention.

  • Fully hosted in the cloud
  • No local hardware required
  • Automatic engine updates

No on-premise option

VocalGuide does not offer on-premise installations or private cloud deployments. All text input is sent to our servers for synthesis, meaning your data leaves your local network during processing.

This approach simplifies maintenance and scaling, as we manage the underlying infrastructure, ensuring reliability without requiring your team to manage servers or network configurations for the TTS engine.

Standard endpoints

We utilize standard RESTful endpoints, making integration straightforward for developers familiar with common API patterns. The request structure mirrors industry standards, reducing the learning curve for engineering teams.

Key endpoints include /v1/audio/speech for generation and /v1/voices for metadata, allowing easy retrieval of available voices and languages directly within your application logic.

Technical infrastructure

Support channels

Sound wave illustration for: Support channels

VocalGuide prioritizes clear, documented communication over immediate availability. We believe that for API integrations and technical queries, a written record is often more valuable than a transient conversation. Our support structure is designed to ensure every question is answered with precision, allowing engineering and HR teams to reference exact solutions later.

Email only

All support requests, from billing questions to technical debugging, are handled exclusively via email. This ensures that your inquiries are tracked, searchable, and never lost in a queue. You can reach our editorial team at [email protected] and API support at [email protected]. We do not offer a phone number.

No live chat

We do not offer live chat or phone support. This deliberate choice keeps our operational costs low, allowing us to maintain simple pricing without hidden service fees. It also ensures that every interaction is asynchronous, allowing our team to provide detailed, thoughtful responses without the pressure of real-time availability.

Response times

While we do not guarantee specific response windows, our team typically reviews emails during standard business hours. For urgent integration issues, please include your API key and request details in the subject line. We aim to resolve most technical queries within 24 hours.

Contact information

Sound wave illustration for: Contact information

We maintain distinct channels for editorial inquiries and technical support to ensure your questions reach the right team efficiently. Our editorial team handles content and partnership discussions, while our technical staff manages API-related issues and key management.

Editorial email

For editorial inquiries, feature requests, or general partnerships, please contact us at [email protected]. We review all messages and respond during business hours.

API support email

For issues regarding your API key, billing, voice selection, or integration questions, email [email protected]. Our team provides email-only support without live chat, ensuring detailed and documented responses to your technical queries.

General inquiries

For other general questions about VocalGuide, you may use the same address: [email protected]. We aim to respond to all inquiries within 24–48 hours via email.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. His impartial tone ensures clarity and neutrality when delivering regulatory information.

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. W3C WAI: making audio and video accessible
  3. curl documentation
  4. FFmpeg documentation
  5. TRON developer hub: TRC-20
  6. LibriTTS-R paper (arXiv 2305.18802)
  7. IETF RFC 7845: Ogg Opus
  8. openai-node on GitHub
  9. MDN: Web Speech API
  10. LibriVox public-domain audiobooks
  11. LibriTTS-R corpus (OpenSLR 141)
  12. Node.js documentation

More on this site