TTS API Pricing, Voices, and Language Support

By LexiRead editorial team · Updated 2026-11-18

LexiRead provides a straightforward text-to-speech API designed for e-commerce startups. This page details exactly how pricing works, which voices and languages are available, and how to integrate the API into your store’s notification or product description workflows. We focus on cost efficiency and speed, giving you the numbers you need without enterprise bloat.

You will find clear breakdowns of our per-character pricing, the free trial credit, and our USDT top-up process. We also list the eight licensed voices, support for 23 languages, and technical specs like rate limits and SDK compatibility. All information is based on current facts to help you decide if this engine fits your project.

TTS API Pricing, Voices, and Language Support

Frequently asked questions

What is the pricing for the TTS API?

The cost is $10 per 1 million characters, equivalent to $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, with charges returned in full. Accounts start with a $0.50 trial valid for 7 days, and the balance never expires.

Which voices are available?

Eight presets are available: Aria, Nova, Luna, and Sage for female voices; Felix, Milo, Atlas, and Orion for male voices. These voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. Every generated file includes an inaudible watermark marking it as synthetic speech.

Which languages are supported?

Support covers 23 languages: 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 of these languages. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.

How do I top up my balance?

Top-ups are made via USDT on the TRON network (TRC-20) only. The minimum amount is $5, and credits are automatically added within minutes after the transfer. There are no cards, PayPal options, subscriptions, or invoices with VAT. The balance does not expire.

Is my input text used for training?

No. Input text is used exclusively to produce the audio and is not used for training. Generated audio is returned in the response and not stored. Only request metadata, such as time, characters, and status, is kept for billing purposes.

Can I use the generated audio commercially?

Yes. Our voices are based on licensed LibriTTS-R (CC BY 4.0) recordings and public-domain LibriVox readings. Every generated file carries an inaudible watermark that marks it as synthetic speech. This watermark identifies the audio as AI-generated, ensuring transparency for your commercial projects.

How do I integrate with the OpenAI SDK?

Use the official OpenAI SDKs by changing the base_url to https://api.getking11.com/v1 and using your site-specific key. The endpoint is POST /v1/audio/speech with a JSON body matching the OpenAI speech endpoint shape. This allows seamless integration without needing a custom SDK.

What are the rate limits?

Limits are 60 requests per minute per key. Before the first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so under load, a request may wait in a queue. Longer texts should be split into parts of up to 4096 characters.

Pricing and Payment

Sound wave illustration for: Pricing and Payment

LexiRead charges $0.01 per 1,000 characters, making it cost-effective for high-volume product descriptions. Failed requests are free, ensuring you only pay for successful synthesis.

Per-Character Pricing

Per-Character Pricing

The rate is $10 per 1 million characters. Spaces and punctuation count toward the total. This linear pricing model helps e-commerce startups predict costs for catalog updates without enterprise bloat.

Free Trial Credit

Free Trial Credit

Signing in with Google provides $0.50 in credit (approx. 50,000 characters) valid for 7 days. Email-based accounts start with zero trial credit. This allows quick validation of voice quality before committing to larger volumes.

USDT Top-Up

Top-ups use USDT on the TRON network (TRC-20). The minimum deposit is $5, credited automatically within minutes. There are no monthly plans, subscriptions, or VAT invoices. Balance does not expire.

  • USDT on TRON (TRC-20) only
  • Minimum $5 top-up
  • Automatic credit within minutes
  • No cards or PayPal

Supported Voices

Sound wave illustration for: Supported Voices

LexiRead provides eight distinct voice presets designed for e-commerce product descriptions and notifications. The selection balances warm narration with energetic promo styles, ensuring your brand audio remains consistent across different content types.

Female Voices

Aria offers a warm, clear narrator style ideal for detailed product features. Nova provides a bright, upbeat tone suitable for promotional announcements. Luna delivers a soft, storytelling voice for brand narratives, while Sage presents a calm, instructional style perfect for user guides.

  • aria: warm, clear narrator
  • nova: bright, upbeat
  • luna: soft, storytelling
  • sage: calm, instructional

Male Voices

Felix brings an energetic, promo-ready energy for sales alerts. Milo offers a friendly, conversational tone for general updates. Atlas provides a neutral, news-style delivery for standard notifications. Orion delivers a deep, documentary voice for premium brand content.

  • felix: energetic, promo
  • milo: friendly, conversational
  • atlas: neutral, news
  • orion: deep, documentary

Voice Licensing

All voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Every generated audio file carries an inaudible watermark identifying it as synthetic speech.

Supported Voices

Languages

Sound wave illustration for: Languages

LexiRead supports 23 languages, allowing e-commerce startups to localize product descriptions and notifications without managing multiple voice engines. Any voice can speak any supported language, ensuring consistent audio quality across your global catalog.

Accurate language detection reduces configuration errors. If the language field is omitted, the API guesses the language from the script, defaulting to English for Latin text. Explicitly setting the ISO code is recommended for non-English Latin-script content to avoid misinterpretation.

23 Supported Languages

Our API covers major markets including English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Hindi, Russian, and more. This breadth allows you to scale content efficiently across diverse regions while maintaining a single integration point.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Language Detection

The API automatically detects the language from the input text. For Latin-script texts in languages other than English, we recommend explicitly setting the language parameter to ensure accurate synthesis and avoid defaulting to English.

Unsupported Languages

Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, and other languages not listed above are not yet supported. You can still use any of the 8 preset voices for supported languages, as voice and language are decoupled.

API Integration

Sound wave illustration for: API Integration

LexiRead provides a straightforward API for generating product audio. The primary endpoint accepts text and returns synthesized speech files, while auxiliary endpoints list available voices and models.

Endpoint Details

Send a POST request to https://api.getking11.com/v1/audio/speech with your text, voice selection, and desired format. The API returns the audio file directly in the response, allowing immediate integration into your e-commerce workflows.

SDK Compatibility

The request structure mirrors the OpenAI speech endpoint. You can use official OpenAI SDKs by simply changing the base_url to https://api.getking11.com/v1 and applying your LexiRead API key. This ensures rapid integration without learning a new client library.

Rate Limits

Accounts are limited to 60 requests per minute per key. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed. This ensures stable performance for generating product descriptions during peak traffic.

API Integration

Data and Privacy

Sound wave illustration for: Data and Privacy

LexiRead processes your input text exclusively to generate the audio file. We do not use your product descriptions or notification content to train our models, ensuring your proprietary data remains yours.

Input Text Usage

Your text is sent to the engine solely for synthesis. Once the audio is generated, the original text is not retained for any other purpose.

Audio Storage

The generated audio file is returned directly in the API response and is not stored on our servers. You retain full control over your audio assets immediately after retrieval.

Billing Data

We retain request metadata, including timestamp, character count, and status, strictly for accurate billing and usage tracking. This data ensures you are charged correctly for each synthesis.

Data and Privacy

Support

Sound wave illustration for: Support

LexiRead relies exclusively on email for all customer inquiries, keeping communication straightforward and documented. There is no phone support or live chat widget on the site, which helps maintain low overhead and keeps per-character pricing competitive for e-commerce startups.

Email Support

Send your questions to the support address found on the contact page. This single channel ensures every query is tracked and addressed without the noise of multiple platforms.

No Live Chat

We do not offer real-time chat or instant messaging. This deliberate choice removes the cost of maintaining live agents, allowing us to pass those savings on to you through our straightforward per-character rate.

Response Time

Support is handled by email only. While we aim to be responsive, we do not guarantee a specific hour-based response window or prioritize requests based on subject line keywords, ensuring fair treatment for all users.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Build your online stores to scale quickly and attract new customers.

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. Tether (USDT)
  3. openai-node on GitHub
  4. IETF RFC 7845: Ogg Opus
  5. TRON developer hub: TRC-20
  6. openai-python on GitHub
  7. Node.js documentation
  8. LibriTTS-R corpus (OpenSLR 141)
  9. W3C WAI: making audio and video accessible
  10. OpenAI API reference: create speech
  11. LibriTTS-R paper (arXiv 2305.18802)
  12. curl documentation

More on this site