About the SmartVoice API Cloud Text-to-Speech Service

By SmartVoice API editorial team · Updated 2026-11-18

This page explains how SmartVoice API works for teams building voice experiences in smart home and IoT devices. We provide a reliable cloud text-to-speech API that integrates easily with embedded systems and voice assistants. You will find details on our 8 licensed voices, 23 supported languages, and our data policy. Our goal is to simplify voice integration with clear, multilingual audio output.

We are an independent team, not affiliated with major tech brands. This page covers our mission, voice licensing sources, and product facts. If you need to know how we handle your data or how to reach us, you will find that information here. We focus on providing a straightforward API for product teams who need consistent, high-quality synthetic speech without unnecessary complexity.

About the SmartVoice API Cloud Text-to-Speech Service

Frequently asked questions

Who runs SmartVoice API?

SmartVoice API is an independent storefront for the same text-to-speech API used across our network. We operate as a standalone provider optimized for embedded systems and smart home devices, distinct from major tech brands. Each site in our network functions independently, managing its own accounts and keys without affiliation to other voice service providers.

Where do voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. These sources provide the base for our synthetic voices, ensuring clear audio output. Every generated file includes an inaudible watermark to identify it as synthetic speech, distinguishing our output from human recordings.

Is the license CC BY 4.0?

The underlying voice recordings are based on LibriTTS-R, which is licensed under CC BY 4.0. However, the generated audio files themselves are synthetic outputs from our API. The license applies to the source recordings, not necessarily the final synthesized audio you receive via our API endpoint.

What data is stored?

We retain request metadata, including time, character count, and status, specifically for billing purposes. Input text is used only to produce the immediate audio response and is not retained long-term. We do not store the generated audio files after they are returned in the API response.

Is text used for training?

No. Your input text is used solely to generate the requested audio file. We do not use your text data for training our models or improving the engine. Once the audio is generated and returned, the text is not kept for machine learning purposes.

Is audio stored?

No. Generated audio is returned directly in the API response and is not stored on our servers. We only keep request metadata for billing. You are responsible for storing the audio files you receive. We do not maintain a library of your generated clips.

How do I contact support?

Support is available via email only. We do not offer phone support or live chat. You can reach us through the contact page on our site. Please include your account details and API key for faster assistance with your requests or billing questions.

Is there a phone number?

No, there is no phone number for SmartVoice API. All support is handled via email. We do not offer live chat or voice support. Please use the contact form or email address provided on our site for any inquiries regarding your account or API usage.

Our Mission

Sound wave illustration for: Our Mission

SmartVoice API simplifies voice integration by providing a straightforward cloud text-to-speech endpoint. We enable product teams to embed clear, multilingual audio directly into their applications without managing complex infrastructure or using our own SDK. Our solution is designed for developers building connected voice experiences who need predictable, consistent results.

Simplify voice integration

Simplify voice integration

Our API follows a familiar request shape, compatible with standard OpenAI SDKs. You send text and receive an audio file, eliminating the need for custom voice engines. This consistency allows your team to integrate voice features rapidly, whether for a smart speaker or a voice assistant.

Support smart home developers

Support smart home developers

We focus on the specific needs of IoT and smart home environments. Our 8 voice presets and 23 language options ensure your devices sound natural across global markets. The API handles character limits and format conversions, letting you focus on the user experience rather than audio processing details.

  • Optimized for embedded systems and voice assistants
  • Clear output for product teams building connected experiences
  • Supports multiple languages with automatic detection

Provide reliable TTS

Provide reliable TTS

Reliability is core to our design. Requests are processed sequentially, ensuring consistent quality. Failed requests are free, so you only pay for successful synthesis. With a free trial and simple top-up via USDT on the TRON network, you can test integration without upfront costs or complex billing.

Voice Licensing

Sound wave illustration for: Voice Licensing

Our voice models are derived from the LibriTTS-R dataset, ensuring a foundation built on high-quality, clean speech data. This source provides the raw material for the eight distinct presets available in the API, ranging from warm narrators to energetic promo voices.

The underlying recordings originate from LibriVox, offering a vast library of public domain audiobook readings. By leveraging these existing resources, we deliver clear, natural-sounding audio suitable for smart home devices and voice assistants without the need for extensive proprietary recording sessions.

LibriTTS-R source

LibriTTS-R source

The LibriTTS-R dataset serves as the primary source for our voice synthesis engine. It provides clean, high-fidelity audio samples that form the basis of our eight voice presets. This ensures consistent quality across all generated audio files.

CC BY 4.0 license

Our voices are based on recordings licensed under CC BY 4.0. This allows us to process and synthesize the audio while respecting the original creators' rights. You receive clear audio output for your embedded systems without complex licensing overhead.

Public domain readings

The core content comes from LibriVox public domain audiobooks. These readings are free of copyright restrictions, providing a robust library of spoken text. This heritage ensures our voices sound natural and experienced, ideal for voice assistants and smart home interactions.

Data Policy

Sound wave illustration for: Data Policy

SmartVoice API prioritizes your data privacy by ensuring that input text is used solely for the immediate production of audio files and is never retained for training purposes. This guarantees that your specific content remains yours, providing a clear boundary between usage and model development without hidden data harvesting.

Text not used for training

Your input text is processed exclusively to generate the requested audio output. We do not retain or utilize your spoken content to improve our underlying speech synthesis models, ensuring your proprietary scripts and product descriptions remain distinct from our training datasets.

Audio not stored

The generated audio files are returned directly in the API response and are not permanently stored on our servers after delivery. This minimizes your data footprint and ensures that your voice-enabled product outputs are transient, reducing the risk of long-term data exposure.

Metadata kept for billing

We retain request metadata, including timestamps, character counts, and status codes, strictly for billing accuracy and usage tracking. This information allows us to process charges correctly and helps you monitor your API consumption without retaining the actual voice content itself.

Team and Structure

Sound wave illustration for: Team and Structure

SmartVoice API is an independent storefront for the same text-to-speech API used across our network. We operate without corporate overhead, allowing us to keep the API straightforward and reliable for product teams building connected devices.

We are not affiliated with OpenAI, Google, or any major tech brand. Our infrastructure is independent, and we do not resell third-party models. This independence ensures that our pricing and feature set remain consistent and directly aligned with the needs of IoT developers.

Independent editorial team

We prioritize stability and clear documentation over marketing hype, ensuring that the API behaves predictably across different hardware implementations.

No affiliation with big brands

Unlike many competitors, we do not borrow brand equity from larger players. We are a standalone provider of TTS technology, meaning your integration depends solely on our infrastructure and our specific 8-voice engine, not on a larger ecosystem.

Email support only

We provide support via email to keep communication detailed and searchable. There is no phone number or live chat, which allows us to maintain a lean structure and pass those savings on to you as a lower per-character rate.

Team and Structure

Product Facts

Sound wave illustration for: Product Facts

SmartVoice API delivers clear, multilingual audio for connected devices. Our engine processes text into speech with consistent quality, ensuring your voice assistants and smart home interfaces sound natural and responsive.

The service is built for developers who need reliability without complexity. We provide straightforward integration paths so your product team can focus on user experience rather than audio engineering details.

8 voices available

Choose from eight distinct presets: aria, nova, luna, and sage for female tones; felix, milo, atlas, and orion for male tones. Each voice is optimized for specific use cases, from warm narration to energetic promos.

23 languages supported

Support covers Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any supported language.

OpenAI SDK compatible

Use the official OpenAI SDKs by pointing them to our base URL. The request shape matches the OpenAI speech endpoint exactly, making migration simple for existing integrations.

Contact Information

Sound wave illustration for: Contact Information

We prefer clear, asynchronous communication for our technical partners. Email is the most reliable channel for support inquiries, ensuring your questions are logged and addressed with care by our team.

We keep our structure simple and independent. You won’t find complex phone trees or expensive live chat agents waiting for you. Just direct, honest support when you need it.

Email support

Send your questions to [email protected]. Please include your API key and a description of the issue for faster resolution.

No phone number

We do not maintain a dedicated phone line. This allows us to keep overhead low and pass those savings directly to you in the form of competitive pricing for your smart home voice integrations.

No live chat

There is no real-time chat widget on this site. For immediate needs during development, our documentation and API reference are the best resources. For specific account issues, email remains our primary support channel.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Connect devices seamlessly to deliver intuitive, responsive living experiences.

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. IETF RFC 7845: Ogg Opus
  3. TRON developer hub: TRC-20
  4. LibriTTS-R corpus (OpenSLR 141)
  5. Creative Commons Attribution 4.0
  6. Node.js documentation
  7. FFmpeg documentation
  8. openai-python on GitHub
  9. Tether (USDT)
  10. MDN: Web Speech API
  11. OpenAI API reference: create speech
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site