Frequently asked questions
Is this the official NaturalReader API?
No, Lectera is an independent API. We are not affiliated with NaturalReader, OpenAI, or any other brand. Our endpoint structure is compatible with standard tools, allowing for minimal configuration changes. We are a standalone service designed specifically for high-volume educational content generation.
How many characters can I process at once?
Each API request accepts up to 4,096 characters of input text. For longer course modules, you can split the text into chunks, generate the audio for each part, and join the resulting files. This ensures consistent quality and manageable processing loads for your LMS integration.
Do voices support multiple languages?
Yes, all eight voices can speak any of our 23 supported languages, including English, Spanish, German, Japanese, and Arabic. You can optionally specify the language code; otherwise, the system guesses from the script. Latin text defaults to English if no language is specified.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are only billed for successful audio generation. This ensures that temporary processing errors do not impact your character count or balance, providing predictable cost management for your team’s daily API usage.
Can I use this with my existing LMS?
Yes. Our API uses a standard JSON format compatible with common HTTP clients, allowing seamless integration into your LMS workflow via POST requests. Since we do not offer a proprietary SDK, you can easily integrate using standard libraries or plain HTTP requests, ensuring flexibility for your existing infrastructure.
Is there a limit on team members?
There are no limits on team members or seats. Our pricing is based on usage, not on the number of users. You can distribute your API key among your team for large-scale course production without worrying about per-user licensing fees or additional overhead costs.
How do I pay for the service?
We accept USDT on the TRON network (TRC-20) for top-ups. The minimum top-up is $5, and credits are added automatically within minutes. We do not accept credit cards, PayPal, or offer monthly subscriptions. Your balance does not expire, and there are no minimum spend requirements.
Do credits expire after the trial?
No, your balance does not expire. The $0.50 trial credit is valid for 7 days, but any additional funds you add via USDT top-up remain available indefinitely. This allows your team to pause large course projects without losing your prepaid audio generation credits.
Are the voices real people or AI?
Our voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark marking it as synthetic speech. We do not offer custom voice cloning or celebrity impersonations.
Can I change my API key?
Yes, you can issue a new API key at any time from your account dashboard. When you generate a new key, the old one stops working immediately. This allows you to securely rotate credentials if you suspect a leak or need to reset access for your team.
What audio formats are available?
We support MP3, WAV, OPUS, FLAC, and PCM formats. You can specify the desired format in your request body. This flexibility allows you to choose the best balance between file size and quality for your specific LMS requirements or archival needs.
Does the API support speed adjustment?
Yes, you can adjust the speech speed between 0.25 and 4.0 times the normal rate. This allows you to create faster summaries or slower, clearer explanations for students. The speed parameter is included in your JSON request body alongside the text and voice selection.
Is my course content data private?
Input text is used only to produce the audio and is not used for training models. Generated audio is returned in the response and not stored on our servers. We keep request metadata like time and character count only for billing purposes, ensuring your course content remains private.
How fast is the synthesis process?
Typical speed is roughly real-time, generating about 25 characters per second of audio. Short phrases may take a few seconds, while longer texts are processed sequentially. Under load, requests may wait in a queue, but performance remains consistent for standard volume usage.
First request
curl
curl https://api.play78e.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 Teams Choose This API
Lectera simplifies audio generation for large online course teams. Our API integrates directly into your LMS workflow, allowing you to convert text to speech without building custom middleware. Just send a JSON payload, and receive high-quality audio files ready for your modules.
We charge $10 per million characters, ensuring predictable costs for bulk content creation. Failed requests are free, and your balance never expires. There are no monthly minimums, so you only pay for what you actually use.
Simple Integration for LMS Workflows
Our API uses a standard JSON format compatible with the OpenAI SDK. You can easily swap the base URL and start generating audio for your courses. This simplicity means your team can focus on content, not infrastructure.
- Standard JSON request body
- Compatible with OpenAI SDKs
- Easy integration into existing LMS
Predictable Character-Based Pricing
Costs are based on input characters, including spaces and punctuation. At $10 per million characters, you know exactly what each course will cost. This transparency helps you budget for large-scale content production.
No Monthly Minimums or Seat Limits
Start with a free trial of $0.50 credit. Add funds via USTRC-20 whenever needed. There are no seats to manage or monthly fees to worry about, making it easy to scale up or down.
High-Quality Synthetic Voices
Lectera provides eight distinct voice presets engineered for educational content. These voices are based on licensed recordings from the LibriTTS-R dataset (CC BY 4.0), sourced from LibriVox public-domain audiobook readings. This foundation ensures consistent, high-fidelity synthetic audio suitable for professional course delivery.
8 Distinct Voice Presets
Our API offers four female and four male voices, each with a specific tonal character. Options include Aria, Nova, Luna, and Sage, alongside Felix, Milo, Atlas, and Orion. This variety allows course teams to assign distinct personalities to different modules or instructors, keeping learner engagement high across long series.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Warm Narrators and Clear Instructors
Voice selection directly impacts how learners receive information. Sage provides a calm, instructional tone ideal for complex tutorials, while Nova offers a bright, upbeat delivery for introductory modules. Atlas delivers a neutral, news-style clarity perfect for factual content, and Orion’s deep voice suits documentary-style courses. Each voice can speak any of our 23 supported languages, allowing consistent branding across global curricula.
Inaudible Watermarking for Synthetic Audio
Every generated audio file contains an inaudible watermark marking it as synthetic speech. This feature helps maintain transparency in your educational materials, clearly distinguishing AI-generated content from human-recorded lectures without affecting audio quality or listener experience. It provides an additional layer of trust for your course participants.

Support for 23 Languages
Our API supports 23 languages, covering major markets for educational content. You can generate courses in Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. This range allows learning teams to localize materials efficiently without managing multiple voice providers.
Global Reach for Course Content
Teams can produce high-quality audio for diverse student bases using a single API key. Whether your curriculum targets German-speaking regions or Japanese learners, the same 8 voice presets deliver consistent quality across all supported languages. This simplifies infrastructure for global course teams.
Automatic Language Detection
When you omit the language field, the system guesses the language from the script. Latin-script text defaults to English, while other scripts trigger appropriate models. This reduces configuration overhead for standard English content, though manual overrides are recommended for non-English Latin text to ensure accuracy.
Manual Language Override Options
Pass the language parameter with an ISO code to force specific language output. This ensures precise delivery when the input text might otherwise be misidentified. It guarantees that your course audio matches the intended linguistic style, avoiding unintended default behaviors for mixed-language scripts.
Developer-Friendly API
The API mimics the OpenAI speech endpoint, allowing you to reuse existing codebases. Simply update the base_url to https://api.play78e.com/v1 and supply your key. This compatibility lets large teams integrate quickly without adopting a new proprietary protocol or rewriting their TTS logic.
OpenAI SDK Compatible
Use the official OpenAI SDKs by changing the base URL. This means your existing Python, Node.js, or Go libraries work immediately. You only need to swap the endpoint and authentication header, reducing integration friction for engineering teams.
Standard JSON Request Format
Send a standard JSON body with model, input, voice, and response_format. The structure mirrors the OpenAI speech endpoint, ensuring consistency. Supported formats include mp3, wav, opus, flac, and pcm, with optional speed and language parameters.
Easy Curl Examples
Start immediately with a ready curl example. The API key page displays a complete request template, including the authorization header and sample payload. This allows developers to test connectivity and voice output within minutes of signing up.
Transparent Pricing Model
Our pricing is straightforward and scales with your usage. You pay only for what you consume, with no monthly minimums, seat limits, or hidden fees. This model is ideal for large online course teams that need predictable costs regardless of fluctuating content volume.
$10 Per Million Characters
The rate is fixed at $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward this total. This simplicity helps you forecast project costs accurately without complex tier calculations.
Free Failed Requests
If synthesis fails, the charge is returned in full. You never pay for audio that wasn't successfully generated, ensuring you only cover usable output for your courses.
No Expiring Credits
Top-up balance does not expire. While the initial $0.50 trial credit is valid for 7 days, your purchased credits remain available indefinitely until used. This allows flexible timing for bulk content generation without pressure.

Data Privacy for Education
Lectera’s TTS API is designed with educational data privacy in mind. When you send text for synthesis, it is used solely to generate the audio file and is never ingested into our training datasets. This ensures that your proprietary course content, lecture notes, and scripts remain private and are not repurposed for model improvement.
Input Text Not Used for Training
Your input text is processed in real-time to create audio and is not stored for training purposes. This guarantees that your unique educational material remains yours, protecting sensitive curriculum data from being used to refine our underlying AI models.
Audio Not Stored After Delivery
Once the audio file is returned in the API response, it is not persistently stored on our servers. This minimizes the attack surface and ensures that your generated voiceovers are delivered to your LMS without lingering copies in our infrastructure.
Minimal Metadata Retention
We retain only the necessary metadata—such as request time, character count, and status—for billing and operational transparency. This limited retention policy ensures that your usage data is kept to the absolute minimum required to support your account.
Fast Processing for Bulk Content
Synthesis runs at roughly real-time speed, generating approximately 25 characters of text per second. Short phrases typically require a few seconds to process, while longer texts scale linearly with their length.
Real-Time Synthesis Speed
Requests are processed sequentially, meaning generation latency scales directly with input length. For standard educational content, this predictable rhythm allows teams to estimate processing times accurately without complex infrastructure calculations.
Queue Management for High Volume
Under heavy load, requests may wait in a queue before processing begins. This ensures stable throughput for large course teams without sudden drops in service quality or unpredictable delays.
Consistent Output Quality
Long texts are split into parts of up to 4096 characters and joined together. The API handles the concatenation of these audio files, ensuring a continuous listening experience for your students.
Seamless Account Setup
Creating an account on play78e.com is straightforward. You can sign up using your Google credentials or a standard email and password combination. This initial step establishes your unique workspace within the Lectera network, ready for your team’s integration needs.
Google or Email Registration
Registration is instant and requires no complex verification. If you use Google, you immediately receive a $0.50 free trial credit valid for 7 days. Email-based accounts start with a zero balance but offer full access to the API structure and documentation.
- Google or email/password sign-up options
- Instant account creation without delays
- Automatic trial credit for Google sign-ins
Instant API Key Generation
Upon registration, your dashboard displays your active API key immediately. You can begin sending requests to https://api.play78e.com/v1 right away. If needed, you can issue a new key at any time, causing the old one to stop instantly.
- Key displayed on the dashboard
- Instant start for API requests
- Swap keys anytime with immediate effect
USDT Top-Up Options
Funding your account is simple via USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits appear automatically within minutes of your transfer. There are no monthly plans, seats, or invoices to manage.
- USDT (TRC-20) payments only
- Minimum $5 top-up
- Credits auto-credited within minutes

Getting Started Today
Create your account in seconds via Google or email. You immediately receive $0.50 in trial credit, covering approximately 50,000 characters. This allows your team to test quality and integration without any commitment or credit card required.
Explore the full range of eight distinct voices and verify the list of supported languages. Once you are ready for production, top up your balance with USDT on the TRON network for instant, automatic credit.
Sign Up for Free Trial
Register on the /get-api-key/ page using your Google account or email. Your account is created instantly, and the trial credit activates immediately, giving you room to experiment with different voice models and speeds.
- Google or email registration
- $0.50 trial credit
- No credit card required
View Available Voices
Check the /v1/voices endpoint to see all eight presets, from warm narrators to energetic instructors. You can also review the supported languages and audio formats to ensure they match your course content requirements.
- Eight voice presets
- 23 supported languages
- Multiple audio formats
Start Your First Request
Use your API key with the OpenAI SDK or a simple curl command. Send your first text to the speech endpoint and receive an audio file. Failed requests are free, so you can refine your workflow without worrying about costs.
- OpenAI SDK compatible
- Simple JSON request
- Free failed requests
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Our scalable platform streamlines employee onboarding and continuous learning across your entire global workforce.
23 languages
Any voice speaks any of these languages.
