Frequently asked questions
Is this text to audio software suitable for small online stores?
Yes. The API charges $10 per 1 million characters with no monthly plans or minimum spend, making it cost-efficient for startups. Accounts created via Google sign-in start with a $0.50 free trial valid for 7 days. Email-based accounts begin without trial credit. You only pay for what you use, allowing you to scale usage for product notifications and descriptions without upfront commitment.
How much does it cost to generate audio for product descriptions?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, and you receive a full refund if synthesis fails. There are no monthly fees, seats, or subscriptions, so you only pay for successful generations.
Can I use the same API key for development and production?
Yes. Each account has one active key that works for both development and production environments. You can issue a new key at any time, which immediately stops the old one. This allows you to rotate keys securely without managing multiple credentials for different stages of your store's development.
What happens if a request fails? Is it charged?
Failed requests are free. If synthesis fails, the charge is returned in full. You only pay for successful audio generations. This ensures you are not billed for errors, making the API reliable for automated product description workflows where occasional glitches might occur during high-volume processing.
Does the API support multiple languages for international stores?
Yes, it supports 23 languages including English, Spanish, German, French, Chinese, Japanese, and Arabic. Any voice can speak any of these languages. You can optionally specify the language code; otherwise, the system guesses it from the script, defaulting to English for Latin text without a specified language.
Are the voices based on real human recordings?
Yes. The eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated file carries an inaudible watermark marking it as synthetic speech. This provides a natural sound foundation without requiring custom voice cloning.
Can I stream audio while it is being generated?
No. The API returns the complete audio file in the response after generation. There is no streaming, WebSocket, or real-time partial audio support. You must wait for the synthesis to complete before receiving the file. This simplifies integration but means you cannot play audio incrementally during generation.
Is there a limit to the length of text per request?
Yes, each request supports up to 4,096 characters. For longer product descriptions, you must split the text into parts, generate audio for each, and join the files. This approach ensures consistent quality and stays within the API's processing limits while allowing you to handle lengthy catalog items effectively.
Do I need to pay monthly for the API access?
No. There are no monthly plans, subscriptions, or minimum spend requirements. You pay only for the characters you generate. Top up your balance using USDT on the TRON network (minimum $5), and the balance does not expire. This pay-as-you-go model is ideal for e-commerce startups with variable traffic, ensuring you cover costs for product descriptions and notifications without enterprise bloat.
How fast is the audio generation compared to real time?
Generation is roughly real-time on long texts, processing about 25 characters per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. This speed is suitable for on-demand product description generation.
Can I use the generated audio in my mobile app?
Yes. The API returns standard audio files (mp3, wav, opus, flac, pcm) that can be stored or played in any mobile app. There is no official mobile SDK, but you can use the OpenAI SDK or plain HTTP requests. The audio files are returned in the response and not stored by us.
Is there a free trial available for new users?
Yes. Google sign-ups receive $0.50 credit (7 days, ~50,000 characters). Email accounts start with zero trial credit. Use this to test integration before topping up with USDT. Failed requests are free, so you can verify voice quality and speed without risk. This trial helps e-commerce startups evaluate cost efficiency for product descriptions before committing to paid usage.
What payment methods are accepted for top-ups?
We accept USDT on the TRON network (TRC-20) only. The minimum top-up is $5, and credits are added automatically within minutes. We do not accept cards, PayPal, or invoices, and there is no VAT. This method avoids traditional payment processing fees, ensuring your balance remains available for immediate use without subscription overhead.
Does the API support SSML for custom pronunciation?
No. The API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You can only control speed, voice, and language. If you need specific pronunciation, you must adjust the input text directly. This keeps the API simple and fast, focusing on core text-to-speech functionality without complex markup.
First request
curl
curl https://api.getking11.com/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Why E-commerce Startups Need TTS
Text-to-speech APIs allow e-commerce startups to convert product descriptions and order updates into audio without hiring voice actors. By sending text to a simple API endpoint, you receive an audio file ready for web playback, automating content generation at scale.
Automating Product Descriptions
Startups can automatically generate audio for thousands of SKUs. With a limit of 4096 characters per request, you can convert detailed product specs into spoken content. For longer descriptions, split the text into parts and join the resulting audio files.
- Convert long product specs by splitting text into 4096-character chunks
- Join generated audio files for continuous playback
- Use narration voices like Aria or Luna for storytelling
Voice Notifications for Orders
Replace static email text with voice notifications for order status. The API processes requests sequentially, so under load, a request may wait in a queue. Short phrases take a few seconds, but longer updates generate at roughly real-time speed (25 characters per second).
- Short phrases take a few seconds to generate
- Longer texts generate at roughly real-time speed
- Requests are processed sequentially, potentially causing queue latency
Accessibility Compliance
Audio content helps meet accessibility standards for visually impaired customers. Each generated file carries an inaudible watermark marking it as synthetic speech, ensuring transparency. Input text is used only for synthesis and not for training, keeping customer data private.
API Architecture Overview
LexiRead’s API accepts JSON payloads via POST requests to generate audio files. The structure mirrors standard TTS endpoints, accepting parameters for text input, voice selection, and audio format. This design allows e-commerce platforms to integrate voice generation directly into their existing product description or notification workflows without complex custom logic.
JSON Request Structure
Requests are sent to the /v1/audio/speech endpoint with a JSON body containing the model, input text, voice preset, and response_format. The system processes these fields synchronously, returning the audio file upon completion. Text exceeding 4096 characters must be split by the client application before submission.
- Endpoint: POST https://api.getking11.com/v1/audio/speech
- Input: JSON body with text, voice, and format parameters
- Limit: 4096 characters per single request
OpenAI SDK Compatibility
The API uses the same request shape as the OpenAI speech endpoint. Developers can reuse existing OpenAI SDKs by simply changing the base_url to https://api.getking11.com/v1. This reduces integration time for teams already familiar with standard TTS libraries, requiring only an update to the authentication header with the LexiRead key.
Endpoint Compatibility
Beyond speech generation, the API provides GET /v1/voices to list available voices and formats, and GET /v1/models for engine details. These endpoints allow dynamic fetching of supported options, enabling e-commerce dashboards to let users select voices or check available languages programmatically without hardcoding values.

Voice Catalog Analysis
The API provides eight distinct voice presets, allowing e-commerce startups to match audio tone to content type without manual design work. Each voice is derived from licensed recordings, ensuring clear, professional output for product descriptions and notifications.
Narrative Voices for Stories
Aria offers a warm, clear narrator style suitable for brand stories. Luna provides a soft, storytelling tone ideal for engaging product narratives.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling
Clear Voices for Instructions
Sage delivers a calm, instructional voice perfect for user guides or checkout flows. Nova adds a bright, upbeat energy for promotional updates.
- Sage: Calm, instructional
- Nova: Bright, upbeat
Neutral Voices for News
Atlas ensures neutral, news-style delivery for order status updates. Orion provides a deep, documentary tone for detailed product specifications.
- Atlas: Neutral, news
- Orion: Deep, documentary
Language Support for Global Stores
LexiRead supports 23 languages, including English, Spanish, French, German, Chinese, Japanese, and Arabic. Any voice can speak any of these languages, allowing a single engine to handle global storefronts without managing multiple voice providers. This simplifies infrastructure for e-commerce startups selling internationally.
If the language field is omitted, the API guesses the language from the script. Latin script text defaults to English. For non-English Latin-script text, you must set the language parameter to ensure accurate pronunciation. This prevents mispronunciation of product names or descriptions in mixed-language content.
Core 23 Languages
The API handles Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Every voice preset works across all 23 languages, ensuring consistent tone and quality regardless of the target market.
- Arabic, Chinese, Danish, Dutch, English, Finnish
- French, German, Greek, Hebrew, Hindi, Italian
- Japanese, Korean, Malay, Norwegian, Polish, Portuguese
- Russian, Spanish, Swahili, Swedish, Turkish
Latin Script Detection
The API detects language from the input script when language is not set. Text in Latin script defaults to English. If your product descriptions are in French or German but use Latin characters, you must explicitly set the language parameter to avoid default English pronunciation.
Missing Languages
Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, and all other languages are not supported. If your store targets these regions, you will need a separate voice provider or manual audio files for those specific languages.
Pricing Model Breakdown
LexiRead uses a straightforward per-character billing model at $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests receive a full credit refund, ensuring you pay only for successful audio generation.
Per Character Rates
Each request processes up to 4,096 characters. For longer product descriptions, split the text into parts and join the resulting audio files. The rate remains consistent regardless of voice choice or audio format selected.
Failed Request Credits
If synthesis fails, the charge is returned in full. This ensures you pay only for successfully generated audio files, protecting your budget during high-volume integration testing or peak sales periods.
No Hidden Fees
There are no monthly plans, seats, or minimum spends. Top-ups use USDT on the TRON network (TRC-20) only, with a $5 minimum. Balances do not expire, and credits are credited automatically within minutes after transfer.

Performance Metrics
Synthesis speed depends on input length. Short phrases require a few seconds, while longer texts generate at roughly real-time (25 characters per second). Processing is sequential, so requests wait in line under load.
Generation Speed
Short phrases typically take a few seconds to synthesize. Longer texts process at roughly real-time speed, averaging 25 characters of text per second of generated audio.
Queue Latency
Requests are processed one after another. Under heavy load, a request may wait in a queue before synthesis begins. For individual product pages, this delay is usually negligible, but it may accumulate during high-volume catalog updates.
Character Limits
Each API request accepts up to 4096 characters. For longer product descriptions or notification sequences, you must split the text into chunks, generate audio for each part, and join the resulting files.
Failed requests are free, ensuring you only pay for successful synthesis.
Data Privacy & Licensing
Input text is used solely to generate the requested audio file and is not retained for training purposes. While request metadata such as timestamps, character counts, and status are stored for billing accuracy, the actual voice content is not stored after the response is delivered.
Training Data Policy
Your product descriptions and notification texts are processed only for the immediate generation task. We do not use your input data to improve the model or train future voice variants, ensuring your commercial copy remains distinct from our training corpus.
Audio Watermarking
Every generated audio file contains an inaudible digital watermark that identifies the content as synthetic speech. This provides clear provenance for your media assets without requiring manual tagging or additional licensing fees for verification.
Voice Source Licenses
Our voice presets are derived from licensed recordings from the LibriTTS-R dataset, which is licensed under CC BY 4.0. These sources originate from LibriVox public-domain audiobook readings. This foundation allows us to offer a diverse set of voices while maintaining clear legal provenance for your commercial use cases.
Integration Complexity
Integration requires no custom SDK, leveraging standard HTTP calls compatible with the OpenAI SDK. Developers simply adjust the base URL to https://api.getking11.com/v1 and use the official library. This eliminates boilerplate code, allowing e-commerce teams to integrate voice generation directly into their existing product description pipelines or notification systems without learning a proprietary client.
No Custom SDK Required
You can use the official OpenAI SDK or plain HTTP requests. The API endpoint shape matches the standard speech endpoint, meaning you only need to change the base URL. This approach avoids vendor lock-in and reduces the learning curve for developers already familiar with common TTS integrations.
Standard HTTP Calls
Send a POST request to /v1/audio/speech with a JSON body containing model, input, voice, and optional parameters like speed or language. The API returns the audio file directly in the response. This straightforward structure fits easily into any backend service, from Python scripts to Node.js microservices handling order confirmations.
Authentication Flow
Include your API key in the Authorization header as Bearer tts-... You can generate or rotate keys via the /get-api-key/ dashboard. Each account holds one active key; issuing a new one immediately invalidates the previous key, simplifying credential management without the complexity of managing multiple service accounts or seats.

Final Verdict for Startups
LexiRead offers a straightforward, low-risk entry into TTS for e-commerce startups. With no monthly plans, no seats, and no minimum spend, you only pay for what you use. The pricing model is transparent: $10 per 1 million characters, with failed requests refunded in full. This cost efficiency allows you to scale audio generation for product descriptions or order notifications without negotiating enterprise contracts or managing complex infrastructure.
The integration process is streamlined for developers. Using standard HTTP calls compatible with the OpenAI SDK, you can implement voice features quickly. Authentication is simple with a single Bearer token, and the lack of custom SDK requirements reduces onboarding time. This ease of integration makes it ideal for small teams needing reliable audio output without heavy engineering overhead.
Cost Efficiency
The per-character billing model ensures you only pay for actual usage. At $10 per 1 million characters, costs are predictable and low. Failed requests are free, protecting your budget. There are no hidden fees, subscriptions, or minimum spend requirements.
Startups can start with a free $0.50 trial valid for 7 days. Top-ups via USDT on TRON are minimal ($5 minimum) and credit automatically. This flexibility supports varying volume needs without long-term commitments.
- $10 per 1 million characters
- Failed requests are free
- No monthly plans or subscriptions
- Start with $0.50 trial credit
Ease of Integration
The API follows a standard JSON structure, compatible with the official OpenAI SDK by simply changing the base URL. This means you can use familiar libraries and tools without learning a new proprietary system.
Authentication uses a single Bearer token, simplifying security management. You can issue a new key at any time, with the old one stopping immediately. This reduces administrative overhead and keeps your API keys secure.
- OpenAI SDK compatible
- Standard JSON request structure
- Single Bearer token auth
- Instant key rotation
Suitability for SMBs
LexiRead is designed for small to medium businesses that need reliable TTS without enterprise bloat. The 8 voice presets cover most e-commerce use cases, from narrations to notifications.
Support is via email only, which is sufficient for startups that do not need 24/7 live chat. The platform’s focus on core functionality ensures that you can implement voice features quickly without managing complex infrastructure or negotiating custom contracts.
The lack of SLAs and certifications is a trade-off for lower costs. For most e-commerce startups, this is an acceptable trade-off given the simplicity and affordability of the service.
- No enterprise contracts
- Email support only
- Core functionality focused
- No SLA or certifications
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.
23 languages
Any voice speaks any of these languages.
