About NodeVoice: Independent Text-to-Speech API

By NodeVoice editorial team · Updated 2026-11-18

This page outlines the operational structure of NodeVoice, an independent storefront for the NodeVoice text-to-speech API. We provide deterministic pricing and standard-compliant endpoints designed specifically for indie developers building smart home and IoT applications. Our model ensures you integrate natural voice responses into your hardware without managing complex infrastructure.

Unlike larger platforms, we operate without corporate affiliation or enterprise overhead. This page details our voice licensing sources, data privacy policies, and technical constraints. It serves as a factual reference for developers who require transparent information about our infrastructure, support channels, and the specific limitations of our synthetic speech engine before integration.

About NodeVoice: Independent Text-to-Speech API

Frequently asked questions

Are you affiliated with OpenAI?

No. NodeVoice is an independent storefront. While the API endpoint structure matches the OpenAI speech endpoint for compatibility, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons.

Who owns the voices used in the API?

The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We use these licensed sources to provide the eight voice presets available in the API.

Do you sell user data to third parties?

No. 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. Request metadata is kept solely for billing purposes.

How can I contact support?

Support is available by email only. We do not offer a phone number, live chat, or on-site support. Please use the contact page to reach our team regarding your account or API usage.

Is the API open source?

No. We do not provide an official SDK of our own, nor is the API source code open. You can use the official OpenAI SDKs by changing the base_url or use plain HTTP requests.

Do you offer enterprise contracts?

No. We do not offer SLAs, uptime guarantees, or enterprise contracts. There are no monthly plans, seats, or minimum spends. Pricing is deterministic at $10 per 1 million characters for all users.

Can I get a SOC 2 certification?

No. We do not provide certifications such as SOC 2, HIPAA, or GDPR certificates. We focus on providing reliable audio synthesis without the overhead of enterprise-grade compliance documentation for independent developers.

Do you have a physical office?

The provided facts do not specify a physical office location. We operate as an independent storefront for the API, managing accounts and billing digitally without requiring physical presence for our developer customers.

Are the voices synthetic or real recordings?

The voices are based on licensed recordings from LibriVox. Every generated file carries an inaudible watermark that marks it as synthetic speech.

Do you store the generated audio files?

No. Generated audio is returned in the response and not stored by our servers. Only request metadata, such as time, characters, and status, is kept for billing and account management purposes.

Can I use the voices in my commercial product?

Yes. The voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. You can integrate these voices into your smart home or IoT applications without additional licensing fees beyond the API usage cost.

Is the CC BY 4.0 license required for output?

The source recordings are under CC BY 4.0. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings.

Do you offer refunds for top-ups?

Failed requests are free, and the charge is returned in full. For top-ups via USDT on TRON, balances do not expire. Failed requests are free: if synthesis fails, the charge is returned in full.

Can I request a specific voice addition?

The API provides eight preset voices. We do not offer custom voice cloning or voice design.

Who We Are

Sound wave illustration for: Who We Are

NodeVoice operates as an independent storefront for a single text-to-speech API. We do not manufacture the engine; we provide the infrastructure layer that allows developers to integrate natural voice responses into hardware and software without managing backend services. Our model ensures deterministic pricing and standard-compliant endpoints tailored for embedded systems and edge computing.

We are a small, focused team dedicated to serving indie developers in the smart home and IoT sectors. Our structure is lean, prioritizing direct communication and technical reliability over corporate bureaucracy. This allows us to maintain strict adherence to our API specifications and pricing models without the overhead of larger enterprise structures.

Independent Storefront Model

Independent Storefront Model

Each NodeVoice instance functions as an independent storefront for the same underlying TTS API. This means you interact with a consistent endpoint (POST https://api.play29p.com/v1/audio/speech) regardless of the specific portal you access. The architecture is designed to be transparent: you send text, receive an audio file, and manage keys directly through the account dashboard.

Editorial Team Structure

Editorial Team Structure

We do not have large marketing departments or sales teams.

No Corporate Affiliation

No Corporate Affiliation

NodeVoice is not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other major tech brand. While our API endpoint shape mimics the OpenAI speech endpoint for ease of use, we are a separate entity. We do not use OpenAI’s models, nor do we guarantee compatibility with their broader ecosystem. Our pricing, voice sets, and infrastructure are entirely independent.

Voice Licensing and Sources

Sound wave illustration for: Voice Licensing and Sources

NodeVoice utilizes licensed recordings from the LibriTTS-R dataset to power its eight voice presets. These voices are derived from public-domain audiobook readings available via LibriVox, ensuring a foundation of high-quality, natural speech suitable for IoT applications.

Each generated audio file contains an inaudible watermark that clearly marks the content as synthetic speech, providing transparency for downstream applications and compliance tracking.

LibriTTS-R License

LibriTTS-R License

The voice models are based on the LibriTTS-R dataset, which provides a robust set of recordings optimized for text-to-speech synthesis. The dataset provides the recordings used for the eight voice presets.

CC BY 4.0 Details

The underlying data is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). This license allows for commercial use and modification, provided appropriate credit is given. The voices are based on licensed recordings: LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings.

LibriVox Public Domain Source

The recordings originate from LibriVox, a platform hosting public-domain audiobook readings. By leveraging these existing public-domain resources, we ensure that the voices are free from restrictive proprietary constraints while maintaining high audio fidelity for smart home and embedded systems.

  • Source: LibriVox public-domain audiobooks
  • License: CC BY 4.0
  • Synthetic watermark included in output

Data Policy and Privacy

Sound wave illustration for: Data Policy and Privacy

NodeVoice processes input text solely to generate audio responses. The system does not retain or repurpose the textual content for machine learning model training, ensuring that your specific voice data remains distinct from our training datasets.

Input Text Usage

Text submitted via the API is transmitted to our cloud servers for synthesis and immediately converted into an audio file. This text is not archived for long-term use or analyzed to improve our voice models beyond the immediate generation task.

No Training on Data

We do not use your input text to train or refine our TTS engines. Your data is used exclusively for the purpose of delivering the requested audio response and is not ingested into our training pipelines for future model development.

Audio Storage Policy

Generated audio files are returned directly in the API response and are not permanently stored on our servers. We retain request metadata—including timestamp, character count, and status—for billing and usage verification purposes only.

  • Audio files are returned in the response and not stored.
  • Metadata (time, characters, status) is kept for billing.
  • Input text is not used for training.

Technical Infrastructure

Sound wave illustration for: Technical Infrastructure

NodeVoice operates as a cloud-based text-to-speech API, delivering synthesized audio files via standard HTTP endpoints. This architecture allows IoT devices and edge hardware to receive audio responses without managing local inference infrastructure, ensuring deterministic pricing and consistent performance across distributed deployments.

Cloud-Based Processing

Text is sent to our servers for synthesis, with results returned immediately as downloadable audio files. This model eliminates the need for developers to maintain GPU clusters or manage scaling logic, enabling seamless integration into smart home hubs and embedded software systems.

No On-Premise Option

We do not offer on-premise installations, data-center choices, or certifications (SOC 2, HIPAA, GDPR). The entire synthesis engine runs in our cloud environment, ensuring uniform voice quality and license compliance without requiring local hardware dependencies or complex network configurations.

Standard HTTP Protocol

Communication relies entirely on standard HTTP POST requests, compatible with any language or framework capable of making web requests. This simplicity supports rapid prototyping for indie developers and reliable long-term integration in resource-constrained IoT devices without requiring proprietary SDKs or persistent WebSocket connections.

Technical Infrastructure

Support and Communication

Sound wave illustration for: Support and Communication

NodeVoice operates with a lean structure, meaning our support team is directly involved in product development and infrastructure management. This ensures that technical inquiries regarding API integration, rate limits, or billing discrepancies are handled by individuals with deep knowledge of the TTS engine, rather than passing through generalist support layers.

Email Only Support

All communication is conducted via email. This channel allows for precise attachment of request logs, error codes, and configuration details essential for troubleshooting IoT edge device issues. We avoid voice calls to maintain a written record of every interaction, which aids in resolving complex asynchronous integration problems common in smart home deployments.

  • Direct email contact for all technical and billing inquiries
  • Written record of all support interactions for audit purposes

No Phone or Live Chat

We do not offer phone lines or live chat widgets. This decision reduces operational overhead, keeping costs low for developers who pay only for character usage. The absence of real-time chat means you cannot expect immediate verbal confirmation, but it ensures that every query is documented and searchable.

Response Expectations

Support responses are typically provided within one business day. During high-volume periods, such as major platform updates or billing cycles, response times may extend slightly. For critical API outages, we prioritize technical notifications via our status page and documentation updates rather than individual email replies.

Limitations and Honest Assessment

Sound wave illustration for: Limitations and Honest Assessment

NodeVoice delivers deterministic, standard-compliant speech synthesis via fixed HTTP endpoints. We prioritize reliability and predictable pricing over feature breadth, ensuring consistent performance for embedded systems and edge computing environments.

No Streaming Protocol

The API returns complete audio files upon request completion. There is no WebSocket or chunked transfer support for real-time partial audio, which suits batch processing but not live voice interaction.

No SSML Support

Synthesis relies on plain text input with optional speed and language parameters. Advanced markup for pauses, pronunciation, or emphasis is not supported.

No Custom Voice Cloning

Users select from eight fixed presets. We do not offer voice design, cloning, or uploading of custom voice samples.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. This creates a more consistent user experience across different devices within a smart home or industrial network without manual reconfiguration.

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. Python documentation
  4. Tether (USDT)
  5. FFmpeg documentation
  6. ISO 639 language codes
  7. W3C WAI: making audio and video accessible
  8. Node.js documentation
  9. LibriTTS-R paper (arXiv 2305.18802)
  10. IETF RFC 7845: Ogg Opus
  11. Creative Commons Attribution 4.0
  12. TRON developer hub: TRC-20

More on this site