Frequently asked questions
What is the API base URL?
The API base URL is https://api.play78e.com/v1. You send POST requests to https://api.play78e.com/v1/audio/speech for synthesis. Other endpoints like /v1/voices and /v1/models are also available under this base path for retrieving voice details and model information.
How do I authenticate requests?
Include your API key in the Authorization header as Bearer tts-... You receive one active key per account. If you issue a new key, the old one stops immediately. Ensure your key is valid and active before sending requests to the API.
Which models are available?
Two models are available: tts-1 and tts-1-hd. Both use the same engine and pricing. You can choose either model for your synthesis requests. The models are listed via the GET /v1/models endpoint. There are no other model variants to select from.
Can I use the OpenAI SDK?
Yes, the official OpenAI SDKs work by changing the base_url to https://api.play78e.com/v1. Use your site's key with the standard speech endpoint. This allows you to integrate easily into existing workflows without learning a new client library or installation process.
What response formats are supported?
You can request audio in mp3, wav, opus, flac, or pcm formats. Specify the desired format in the response_format field. This gives you flexibility in handling audio files within your LMS or course delivery systems without needing additional conversion tools.
How do I set the voice speed?
Adjust the speed using the speed field, which accepts values from 0.25 to 4.0. This allows you to control the playback rate of the generated speech. Faster speeds reduce generation time, while slower speeds may improve clarity for complex course content.
What happens if I exceed rate limits?
You are limited to 60 requests per minute per key. If you exceed this, requests may wait in a queue. Before your first top-up, the limit is 10 requests per minute. Exceeding the limit does not incur extra charges, just potential delays.
Do I need to install a specific SDK?
No, you do not need a specific SDK. You can use the OpenAI SDK or plain HTTP requests. There is no official SDK from us, no mobile SDK, and no WordPress plugin. Any HTTP client that can send JSON works perfectly.
How do I handle large texts?
Split your text into parts of up to 4096 characters. Generate audio for each part separately, then join the resulting audio files. This ensures each request stays within the character limit while allowing you to process long course modules or lessons.
Are there character limits per request?
Yes, each request can contain up to 4096 characters of input text. Spaces and punctuation count toward this limit. If your text exceeds this, split it into multiple requests. Each request is processed independently, so plan your splitting strategy accordingly.
Can I change my voice after starting?
Yes, you can change the voice for each request. There are eight preset voices available: aria, nova, luna, sage, felix, milo, atlas, and orion. You specify the voice in the request body, allowing you to vary narration styles across different course sections.
How do I detect the language?
If you do not set the language field, the system guesses it from the script. Latin script defaults to English. For non-English Latin text, explicitly set the language parameter. Supported languages include Arabic, Chinese, English, French, German, Spanish, and others listed in the docs.
What is the maximum text length?
The maximum text length per request is 4096 characters. This includes all spaces and punctuation. For longer content, split the text into chunks of this size. Each chunk generates a separate audio file that you can concatenate into a final course audio file.
How do I get a list of voices?
Send a GET request to /v1/voices. This endpoint returns details about available voices, languages, formats, and pricing. You can also check /v1/models for model information. Use this data to select the appropriate voice and settings for your course content.
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.mp3Python (openai)
from openai import OpenAI
client = OpenAI(base_url="https://api.play78e.com/v1", api_key="tts-...")
with client.audio.speech.with_streaming_response.create(
model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
response.stream_to_file("hello.mp3")Node.js (openai)
import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({ baseURL: "https://api.play78e.com/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));| voice | |
|---|---|
aria | female |
nova | female |
luna | female |
sage | female |
felix | male |
milo | male |
atlas | male |
orion | male |
| language | |
|---|---|
ar | العربية |
zh | 中文 |
da | Dansk |
nl | Nederlands |
en | English |
fi | Suomi |
fr | Français |
de | Deutsch |
el | Ελληνικά |
he | עברית |
hi | हिन्दी |
it | Italiano |
ja | 日本語 |
ko | 한국어 |
ms | Bahasa Melayu |
no | Norsk |
pl | Polski |
pt | Português |
ru | Русский |
es | Español |
sw | Kiswahili |
sv | Svenska |
tr | Türkçe |
Authentication and Keys
Lectera’s API secures your text-to-speech requests using a single active Bearer token per account. This key authorizes all calls to the speech endpoint and tracks your character usage against your balance. You can generate and manage this key directly from your account dashboard.
The token format is a simple string prefixed with tts-, passed in the HTTP Authorization header. Each account maintains only one active key at a time, ensuring clear audit trails for your LMS integration and billing reconciliation.
Generate Your API Key
Visit the /get-api-key/ page to sign in with Google or your email. Your unique API key appears immediately alongside your current balance and usage statistics. No additional configuration is required to start using it with your existing tools.
- Sign up via Google or email/password on the dashboard
- Key is displayed immediately upon login
- One key per account
Bearer Token Format
Include your key in the header as Authorization: Bearer tts-.... This standard format works seamlessly with the OpenAI SDKs and any HTTP client that supports Bearer authentication. Ensure no extra spaces are included in the header value.
Key Rotation Policy
You can issue a new key at any time from your dashboard. When a new key is generated, the previous one stops working immediately. This allows for instant revocation if a key is exposed, with no downtime for your active integrations.
- Generate new key anytime
- Old key stops immediately
- Instant revocation
Endpoints Overview
Lectera’s API exposes three core endpoints designed for seamless integration with your LMS workflow. These endpoints allow your automation scripts to retrieve configuration details and generate audio files programmatically.
Each endpoint follows standard REST conventions, making it easy to integrate with existing Python, Node.js, or PHP scripts used by your course production teams.
Speech Generation Endpoint
Use POST /v1/audio/speech to convert text into audio files. This is your primary endpoint for generating voiceovers for course modules, quizzes, or introductory text.
The endpoint accepts JSON bodies with model, input text, voice selection, and format preferences. It returns the audio file directly in the response body.
- Accepts up to 4096 characters per request
Voices List Endpoint
Call GET /v1/voices to retrieve the full list of available voice presets, supported languages, and audio formats. This helps your team select the right voice for each course segment.
The response includes metadata for all 8 voice presets, ensuring your automation scripts can dynamically match voice types to content tone.
Models Information Endpoint
Access GET /v1/models to view available models and their specifications. This endpoint confirms support for both tts-1 and tts-1-hd models.
Use this endpoint to verify model availability and ensure your integration aligns with the current engine capabilities.

Request Parameters
Lectera’s API delivers high-quality synthetic speech through two distinct engine tiers. Both tts-1 and tts-1-hd utilize the same underlying engine and pricing model, allowing your LMS integration to switch between standard and high-definition audio without changing infrastructure or incurring extra costs per request.
Model Selection (tts-1, tts-1-hd)
Select tts-1 or tts-1-hd for course narration; both use the same engine and pricing. Both options support up to 4,096 characters per request and are billed at the same rate of $10 per million characters.
Voice Preset Selection
Choose from eight licensed voice presets tailored for educational content. Female voices like Aria (warm narrator) and Luna (soft storytelling) suit academic lectures, while Felix (energetic promo) and Milo (friendly conversational) engage learners in marketing modules. Male voices like Atlas (neutral news) and Orion (deep documentary) provide authoritative tones for instructional videos.
Each voice is based on licensed recordings from LibriTTS-R and LibriVox. All generated audio files include an inaudible synthetic watermark for clear identification.
- 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
Response Format Options
Specify the output format via the response_format parameter. Supported formats include mp3, wav, opus, flac, and pcm. MP3 is recommended for general LMS playback due to its balance of quality and file size, while WAV or FLAC may be preferred for high-fidelity archival or editing workflows.
Failed requests are free, ensuring you only pay for successfully generated audio files in your preferred format.
Speed and Language Settings
Adjusting speech speed allows your course narrations to match the pacing of your visual content. You can set the speed between 0.25 and 4.0, enabling everything from slow, instructional clarity to rapid, energetic delivery. This flexibility ensures consistent audio quality across diverse educational materials.
Language support covers 23 languages, including English, Spanish, German, and Japanese. Any voice can speak any of these languages, giving your team uniform vocal quality regardless of the target audience's locale. Precise control ensures your learners hear clear, accurate pronunciation every time.
Adjustable Speed Range
Set the speed parameter between 0.25 and 4.0. Values below 1.0 slow down the narration for complex explanations, while values above 1.0 accelerate the audio for quick reviews or summaries. The API maintains natural intonation across this entire range.
- Minimum speed: 0.25x (half-time) for detailed, slow-paced instruction.
- Maximum speed: 4.0x (four times normal) for rapid content review.
- Default speed: 1.0x for standard, natural narration pace.
ISO Language Codes
Specify the language parameter using standard ISO 639-1 codes (e.g., 'en', 'de', 'ja'). This explicit setting is crucial when your input text uses Latin script but is not in English, preventing the API from guessing the wrong language. Supported codes include those for Arabic, Chinese, French, Hindi, Korean, Portuguese, Russian, and Swedish.
Our system supports 23 languages in total. If you are creating courses for diverse international teams, you can maintain a single voice preset while switching languages seamlessly. This consistency helps build brand recognition across different language versions of your course content.
- Supported languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish.
- Use standard ISO codes like 'es' for Spanish or 'fr' for French.
Automatic Language Detection
If you omit the language parameter, the API guesses the language based on the input text script. Latin script defaults to English, while Cyrillic defaults to Russian, and so on. This feature simplifies integration for single-language courses where you do not want to manage language codes for every request.
For non-English text written in Latin script (e.g., German or Dutch), you must explicitly set the language parameter. Without this, the API will default to English, resulting in an incorrect accent. Explicit language settings ensure your course audio sounds native and professional.
- Latin script defaults to English if no language is specified.
- Cyrillic script defaults to Russian.
- Always set the
languageparameter for non-English Latin script text to ensure correct pronunciation.
OpenAI SDK Integration
Integrate Lectera’s TTS API into your existing LMS workflows using the widely adopted OpenAI SDKs. By simply adjusting the base URL, your team can leverage familiar code structures without learning a new library.
This approach minimizes integration time for large online course teams, allowing you to focus on content creation rather than API configuration.
Base URL Configuration
Update your SDK client’s base_url to https://api.play78e.com/v1. This directs all requests to our speech endpoint while maintaining standard OpenAI compatibility.
Ensure your API key is passed via the Authorization: Bearer <key> header. One active key per account simplifies management for large teams.
- Base URL: https://api.play78e.com/v1
- Standard OpenAI SDKs work directly
- No custom client required
Standard Method Usage
Use the standard speech method with the same request shape as OpenAI. Pass your model, input text, voice, and response_format parameters.
The SDK handles JSON serialization and response parsing, returning audio files ready for playback in your LMS player.
SDK Compatibility Notes
Official OpenAI SDKs are compatible. No proprietary client or additional dependencies are needed.
This ensures stability and long-term maintainability for your course production pipeline.

Curl Example for Testing
Verify your API integration directly from the terminal using a standard HTTP request. This method requires no external libraries, making it ideal for quick validation of your credentials and endpoint configuration before building your LMS workflow.
You can also test voice presets and response formats instantly to ensure the audio output meets your course quality standards without writing code.
Basic Request Structure
Send a POST request to the speech endpoint with your Bearer token in the header. Replace YOUR_API_KEY with the key from your dashboard.
curl -X POST https://api.play78e.com/v1/audio/speech \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{...}'
JSON Body Format
The request body must be valid JSON containing the model, input text, voice preset, and response_format. Text input is limited to 4096 characters per request.
{ "model": "tts-1", "input": "Welcome to your new course module.", "voice": "nova", "response_format": "mp3" }
Audio Output Handling
On success, the API returns the audio file directly in the response body. Save this binary output to a local file, such as output.mp3, for immediate playback or upload to your LMS.
If the request fails, check the HTTP status code and error message in the response for debugging information.
Rate Limits and Quotas
Lectera’s API handles high-volume text-to-speech generation for large course teams with predictable throughput. Understanding your rate limits ensures smooth integration with your LMS workflow, preventing bottlenecks during bulk audio production.
60 Requests Per Minute
Each API key supports up to 60 requests per minute. This limit applies to all synthesis endpoints. For most course production pipelines, this throughput is sufficient when texts are split into 4,096-character segments.
Initial Limit for New Accounts
New accounts start with a lower limit of 10 requests per minute. This applies until you add your first top-up. It allows you to test the integration before committing to higher volume generation.
Limit Increase Process
To increase your rate limit, simply add credit to your account. USDT (TRC-20) transfers are processed automatically within minutes. Once credited, your limit immediately upgrades to the standard 60 requests per minute.

Error Handling and Status Codes
When synthesizing audio for your courses, understanding how the API responds to issues helps keep your LMS workflow smooth. Lectera provides clear status codes and transparent refund policies so you know exactly when a request fails and why.
Errors are standard HTTP codes. Failed synthesis requests are refunded in full, ensuring you only pay for successfully generated audio files.
Common HTTP Error Codes
Use standard HTTP status codes to diagnose issues. 200 indicates success, while 400 errors often stem from invalid JSON or missing fields. 401 errors indicate an invalid or expired API key, and 429 errors signal that you have exceeded the 60 requests per minute limit.
- 400: Bad Request (invalid JSON or parameters)
- 401: Unauthorized (invalid API key)
- 404: Not Found (incorrect endpoint)
- 429: Too Many Requests (rate limit exceeded)
- 500: Internal Server Error (try again later)
Failed Request Refunds
If synthesis fails due to a server-side error, the charge is returned in full. You only pay for successfully generated audio files, ensuring predictable costs for your team’s voiceover production.
Debugging Tips
Check your input text length (max 4096 characters) and ensure the voice parameter matches one of the eight presets. If you encounter persistent 429 errors, consider splitting your text or adjusting your request frequency. Contact support via email for specific account issues.
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.
