About the Editorial Team Behind the TTS API

By Viva Voice Labs editorial team · Updated 2026-11-18

This page details the operational structure and technical foundations of the Viva Voice Labs API, designed for indie developers integrating text-to-speech into call center and IVR workflows. We are an independent editorial and engineering team, not a subsidiary of OpenAI or any other major cloud provider. Our focus remains strictly on delivering a robust, OpenAI-compatible API with transparent character-based pricing and stable rate limits.

You will find precise information regarding our voice licensing model, data handling policies, and support infrastructure. All content here reflects current facts about the API’s capabilities, limitations, and pricing structure. This is not a marketing brochure; it is a factual record of what our system does, how it processes your text, and what you can expect from our email-only support channel.

About the Editorial Team Behind the TTS API

Frequently asked questions

Who runs the Viva Voice Labs API?

Viva Voice Labs operates this independent storefront. We provide a robust text-to-speech API designed for call center operators and indie developers. Our system delivers consistent, licensable synthetic voices with transparent character-based pricing and stable rate limits for high-volume IVR systems.

Are the voices copyrighted?

Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. You may use these voices in your projects under the applicable license terms.

Do you use customer data for training?

Input text is used only to produce the audio and is not used for training. Request metadata, including time, characters, and status, is kept for billing purposes. Generated audio is returned in the response and not stored by our servers.

How can I contact support?

Support is available by email only. We do not offer a phone number or live chat. You can reach us via the contact page or by emailing our support team regarding your account, billing, or technical questions about the API.

Is this an official OpenAI product?

No. We are not affiliated with OpenAI. Our API endpoint shape matches the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by changing the base_url. However, we are an independent provider with our own keys, pricing, and voice models.

What is the LibriTTS-R license?

LibriTTS-R is licensed under CC BY 4.0. Our voices are derived from these recordings. This license allows commercial use provided you give appropriate credit. We also source from LibriVox public-domain readings, which generally require no attribution, though credit is good practice.

Do I need to credit the voice?

Under the CC BY 4.0 license for LibriTTS-R, attribution is required. While LibriVox content is public domain, crediting the source is recommended. Check specific usage requirements for your project. Our generated files include a synthetic watermark to identify them as AI speech.

Are there any uptime guarantees?

We do not provide 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 aim for stability.

Do you store the audio files?

Generated audio is returned in the response and not stored by us. Input text is used only for synthesis and is not retained for training. We keep request metadata, such as time and character count, strictly for billing and account management purposes.

Do you have a physical office?

We do not list a physical office address. Support is handled via email only. We are an independent storefront operating the API infrastructure. You can reach our team through the contact page or by emailing our support address directly.

Is the API open source?

The API itself is not open source. We provide a standard HTTP interface compatible with OpenAI SDKs. The underlying voice models are based on licensed data. We do not release our proprietary code or model weights. Use standard HTTP requests or SDKs.

Can I use the voices in podcasts?

Yes. Our voices are licensable synthetic voices suitable for various media, including podcasts. You can generate audio files in formats like mp3, wav, opus, flac, or pcm. Ensure you comply with the underlying LibriTTS-R or public domain licenses if required by your distribution.

Do you offer refunds?

Failed requests are free; if synthesis fails, the charge is returned in full. We do not offer refunds for successful requests. Balance does not expire. Top-ups via USDT on the TRON network (TRC-20) are credited automatically. No invoices with VAT are issued for standard transactions.

How do I verify the license terms?

Our voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. You can verify CC BY 4.0 terms at creativecommons.org. For specific usage, review the generated audio watermark. We provide no additional certification documents; rely on the source licenses.

Who We Are

Sound wave illustration for: Who We Are

Viva Voice Labs operates as an independent editorial team focused on delivering robust developer tools. We provide a text-to-speech API designed for call center operators and indie developers building high-volume IVR systems. Our structure is lean, ensuring consistent updates and direct accountability without the overhead of a large corporate entity.

We prioritize practical utility over marketing hype. Our team manages the infrastructure, licensing, and documentation for the API, ensuring that developers receive a stable, predictable service. We do not distract from the core product with unnecessary corporate layers or unrelated business ventures.

Independent Editorial Team

Independent Editorial Team

We are not a division of a larger tech giant. Our editorial team manages the API directly, making decisions based on developer feedback and technical stability. This independence allows us to maintain transparent pricing and straightforward rate limits without internal bureaucratic delays.

Focus on Developer Tools

Focus on Developer Tools

Our primary product is the TTS API. We optimize for simplicity and reliability, providing standard JSON requests and OpenAI-compatible endpoints. This focus ensures that indie developers can integrate our voices into their IVR systems quickly, using familiar tools and documentation.

No Corporate Affiliations

No Corporate Affiliations

We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our voices are based on licensed recordings from LibriTTS-R, and our infrastructure is independent. We do not claim ownership or endorsement from these larger entities.

Voice Licensing

Sound wave illustration for: Voice Licensing

Viva Voice Labs delivers synthetic voices derived from licensed recordings, ensuring legal clarity for commercial IVR deployments. Our audio engine utilizes standard presets without proprietary voice design, relying on verified source material to maintain consistent quality across all generated outputs.

LibriTTS-R License

LibriTTS-R License

All voice presets are based on the LibriTTS-R dataset, which carries a CC BY 4.0 license. This allows us to distribute the synthetic audio legally while maintaining the distinct characteristics of the original recordings.

Public Domain Source

The underlying recordings originate from LibriVox public-domain audiobook readings. This source ensures that the base audio material is free from restrictive copyright claims, providing a stable foundation for high-volume call center applications.

Commercial Usage Rights

The CC BY 4.0 license permits commercial use, allowing you to integrate these voices into your IVR systems without additional licensing fees. You retain the right to use the generated audio for business purposes, including customer interactions and automated prompts.

Technology Stack

Sound wave illustration for: Technology Stack

Viva Voice Labs utilizes an OpenAI-compatible API architecture, allowing indie developers to integrate our text-to-speech service using standard tools. By adopting the same request shape as the OpenAI speech endpoint, you can leverage existing OpenAI SDKs simply by changing the base_url to https://api.playmvpviva.com/v1.

Requests are structured as standard JSON payloads sent via POST to https://api.playmvpviva.com/v1/audio/speech. This ensures compatibility with widely used developer libraries without requiring custom wrappers or proprietary client code.

OpenAI-Compatible API

Our API mirrors the structure of the OpenAI speech endpoint. This design choice enables immediate integration for developers already familiar with OpenAI’s ecosystem. You can use official OpenAI SDKs by updating the base_url configuration.

  • Same request shape as OpenAI speech endpoint
  • Compatible with official OpenAI SDKs

Standard JSON Requests

All interactions use standard JSON bodies sent over HTTPS. The endpoint accepts model, input, voice, response_format, speed, and language parameters. Authentication is handled via a Bearer token in the Authorization header.

  • POST /v1/audio/speech endpoint
  • JSON body format
  • Bearer token authentication

Audio Generation Engine

The engine processes requests sequentially, generating audio files based on the selected model (tts-1 or tts-1-hd). Text is synthesized into audio formats like mp3, wav, opus, flac, or pcm. Speed adjustments range from 0.25x to 4.0x.

  • Models: tts-1, tts-1-hd
  • Formats: mp3, wav, opus, flac, pcm
  • Speed: 0.25–4.0

Data Privacy and Usage

Sound wave illustration for: Data Privacy and Usage

Viva Voice Labs processes your input text exclusively for the purpose of generating the requested audio file. The system does not retain the textual content after synthesis is complete, ensuring that your source material remains private and isolated from general data pools.

We maintain strict separation between operational data and content. The input strings you submit are not ingested into our training datasets for future model improvements. This ensures that your proprietary scripts or customer data do not influence the behavior of the underlying voice engine.

Input Text Handling

When you send a request, the text payload is processed in memory to produce the audio output. Once the audio file is generated and delivered in the response, the original text string is discarded. It is not archived for long-term storage or analysis.

  • Text is processed in real-time for synthesis only.
  • No long-term archival of input strings.
  • Input is discarded after audio generation.

No Training Data Usage

Unlike many consumer-grade services, we do not use your submitted text to train or refine our voice models. Your contributions remain distinct from the training corpus, preserving the integrity of your specific data inputs.

This approach ensures that your unique phrasing or specialized vocabulary does not inadvertently alter the voice characteristics available to other users on the platform.

  • Input text is excluded from training datasets.
  • Voice models are updated independently of user submissions.
  • Your data does not influence other users' results.

Audio Storage Policy

The generated audio files are returned directly in the API response and are not stored on our servers after delivery. Each request is treated as a transient transaction.

We retain request metadata—such as timestamp, character count, and status—for billing purposes only. This metadata does not include the actual text or audio content, ensuring that your usage records remain minimal and strictly financial.

  • Audio files are not stored after delivery.
  • Metadata kept for billing only.
  • No retention of audio content.
Data Privacy and Usage

Support and Contact

Sound wave illustration for: Support and Contact

Viva Voice Labs provides email-only support for all API-related inquiries. As an independent editorial team focused on developer tools, we do not maintain a live chat widget or a dedicated phone line for customer service. All communication occurs asynchronously via email to ensure clear, documented resolution of technical issues.

Email Support Only

Send your questions or issue reports to our support email address. We handle all account, billing, and technical queries through this single channel to maintain a streamlined communication process for our indie developer audience.

No Live Chat or Phone

We do not offer real-time phone support or interactive chat widgets. This approach reduces overhead and allows us to focus on maintaining the stability of the TTS API infrastructure rather than staffing a 24/7 call center.

Response Expectations

While we aim for timely replies, response times may vary depending on request volume. Please include your API key and a clear description of the issue in your initial email to expedite the process.

  • Include your API key in all emails
  • Describe the specific endpoint and error message
  • Attach relevant request/response logs if applicable

Limitations and Honesty

Sound wave illustration for: Limitations and Honesty

Viva Voice Labs delivers a focused text-to-speech API without unnecessary complexity. We prioritize reliable, character-based pricing and straightforward integration for indie developers and call center operators who need consistent synthetic voices. Our system is built on standard protocols, ensuring compatibility with existing tools without requiring proprietary SDKs or custom infrastructure.

No Streaming Support

Audio is generated as complete files, not streamed in real-time. This ensures consistent quality and simplifies integration for IVR systems that require full audio buffers before playback. Short phrases may take a few seconds to generate.

No SSML or Custom Lexicons

The API does not support SSML markup or custom pronunciation lexicons. If language is not set, it is guessed from the script (Latin text defaults to English). Users must set the language parameter explicitly for non-English Latin texts.

No SLA Guarantees

We do not offer Service Level Agreements (SLAs) or uptime guarantees. Requests are processed sequentially, meaning high traffic may result in queue delays. Our rate limit of 60 requests per minute is strict, and exceeding it will not incur additional charges but may increase processing time for subsequent requests.

  • No 99.9% uptime guarantee
  • Requests processed sequentially under load
  • Strict 60 req/min rate limit
  • No financial penalties for downtime

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. This voice is optimal for general call center announcements where clarity is paramount.

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. Python documentation
  3. Tether (USDT)
  4. Node.js documentation
  5. IETF RFC 7845: Ogg Opus
  6. openai-node on GitHub
  7. ISO 639 language codes
  8. Creative Commons Attribution 4.0
  9. curl documentation
  10. OpenAI API reference: create speech
  11. FFmpeg documentation
  12. LibriVox public-domain audiobooks

More on this site