Developer Guide for LMS TTS Integration and Setup

By LMS Voice Core editorial team · Updated 2026-11-18

This documentation outlines the technical specifications for integrating LMS Voice Core into your learning management system workflows. It provides precise details on API endpoints, authentication protocols, and data structures required for automated voiceover generation in online course production.

Developers managing large-scale content libraries will find the necessary parameters for voice selection, language handling, and audio format configuration. The guide covers rate limits, error handling, and chunking strategies to ensure reliable delivery of synthetic speech assets directly into your LMS environment.

Developer Guide for LMS TTS Integration and Setup

Frequently asked questions

Do I need a custom SDK to use the API?

No custom SDK is required. The API uses the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.playa1one.com/v1 and providing your site-specific key. Alternatively, you can use plain HTTP requests with standard JSON bodies.

Can I use the OpenAI Python SDK with this API?

Yes. The API endpoint matches the OpenAI speech endpoint structure. You can use the official OpenAI Python SDK by configuring the base_url to https://api.playa1one.com/v1. Ensure you use your specific API key for authentication. This allows seamless integration into existing Python workflows without needing a proprietary client library.

What is the maximum character limit per request?

Each request supports a maximum of 4096 characters in the input field. Spaces and punctuation count toward this limit. For longer texts, split the content into parts of up to 4096 characters and join the resulting audio files. This ensures consistent processing and avoids payload size issues during synthesis.

How do I specify the audio format in the request?

Include the response_format field in your JSON body. Valid formats are mp3, wav, opus, flac, and pcm. This field is optional; if omitted, the API returns a default format. Ensure your LMS backend can handle the selected format for playback or storage within your course infrastructure.

Does the API support streaming audio responses?

A: No, the API does not support streaming or WebSocket connections. Audio is returned as a complete file in the response body. You must wait for the full synthesis to complete before receiving the data. This fits batch processing workflows typical in LMS content generation pipelines.

What happens if I exceed the rate limit?

The limit is 60 requests per minute per key. If you exceed this, requests may queue or fail. New accounts start with 10 requests per minute until the first top-up. Failed requests are free, so exceeding limits does not incur extra charges, but may delay audio generation.

Can I use the API with my own LMS backend?

Yes. The API is a standard cloud endpoint accepting JSON POST requests. You can integrate it directly into your LMS backend via HTTP calls. Use the provided API key for authentication. This allows you to generate audio assets on demand without managing complex infrastructure or third-party plugins.

Is SSML supported for fine-tuning pronunciation?

No, SSML is not supported. The API accepts plain text input only, with no support for phoneme dictionaries or custom pronunciation lexicons. You must rely on the eight voice presets and optional language settings to control output. Fine-tuning is limited to speed adjustments (0.25–4.0) and voice selection.

How do I handle voice selection for multiple languages?

Any of the 8 voices can speak any of the 23 supported languages. Use the language parameter with an ISO code to guide synthesis. If omitted, the API guesses the language, defaulting to English for Latin script. Explicitly setting the language ensures accurate pronunciation for non-English content.

What is the base URL for the API?

The base URL is https://api.playa1one.com/v1. Use this for all API calls, including POST /v1/audio/speech and GET /v1/voices. Ensure your SDK or HTTP client points to this domain. Authentication is handled via the Authorization header with your Bearer token key.

Do I need to store the generated audio files?

A: No, the API does not store generated audio files. The audio is returned directly in the response body. You are responsible for storing the audio in your LMS or cloud storage. Input text is also not stored for training; only request metadata is kept for billing purposes.

Can I adjust the speaking speed of the voices?

Yes, you can adjust the speed using the speed field. Values range from 0.25 to 4.0. This allows you to control the pacing of the narration. Faster speeds reduce generation time but may affect clarity. Adjust this parameter based on the target audience and content type.

Are there any limits on the number of concurrent requests?

A: Requests are processed sequentially, so under load, a request may wait in a queue. There is no explicit concurrent request limit defined, but the 60 requests per minute rate limit applies. High concurrency may increase latency. Plan your batch jobs to avoid queuing delays during peak usage.

How do I rotate my API key?

You can issue a new API key at any time from your account dashboard. The old key stops working immediately upon issuing the new one. Ensure your LMS backend updates to the new key to maintain uninterrupted service. This allows secure key rotation without downtime.

First request

curl

curl https://api.playa1one.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.mp3

Python (openai)

from openai import OpenAI

client = OpenAI(base_url="https://api.playa1one.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.playa1one.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
ariafemale
novafemale
lunafemale
sagefemale
felixmale
milomale
atlasmale
orionmale
language
arالعربية
zh中文
daDansk
nlNederlands
enEnglish
fiSuomi
frFrançais
deDeutsch
elΕλληνικά
heעברית
hiहिन्दी
itItaliano
ja日本語
ko한국어
msBahasa Melayu
noNorsk
plPolski
ptPortuguês
ruРусский
esEspañol
swKiswahili
svSvenska
trTürkçe

Authentication and Keys

Sound wave illustration for: Authentication and Keys

LMS Voice Core uses standard Bearer token authentication. Include your API key in the Authorization header of every request. The key format is tts-... and is unique to your account.

Bearer Token Setup

Bearer Token Setup

Pass the key as Authorization: Bearer tts-your-api-key. This applies to all endpoints, including speech synthesis and voice listing. Ensure the header is correctly formatted to avoid 401 Unauthorized errors.

Key Rotation Policy

Key Rotation Policy

Issue a new key from the dashboard at any time. The previous key becomes invalid immediately upon issuance of the new one. This ensures strict control over access without waiting for expiration periods.

  • Generate new keys instantly via the dashboard.
  • Old keys stop working immediately.
  • No grace period for old keys.

Single Active Key Limit

Each account maintains only one active API key at any given moment. If you need a different key for a specific environment, you must rotate the existing key. This simplifies credential management for L&D teams.

Quickstart with cURL

Sound wave illustration for: Quickstart with cURL

Use cURL to send text directly to the speech endpoint. Replace YOUR_API_KEY with your active token from the dashboard. This method confirms connectivity and returns the audio file immediately.

Ensure the request body matches the required JSON structure. The endpoint accepts standard text inputs up to 4096 characters. Failed requests incur no charge.

Basic POST Request

Send a POST request to https://api.playa1one.com/v1/audio/speech. Include the Bearer token in the Authorization header. The request body must contain the model, input text, and voice preset.

  • Endpoint: POST https://api.playa1one.com/v1/audio/speech
  • Header: Authorization: Bearer YOUR_API_KEY
  • Body: JSON format with model, input, voice.

JSON Body Structure

The body requires model ("tts-1" or "tts-1-hd"), input (text string), and voice (e.g., "aria"). Optional fields include response_format, speed, and language.

  • model: "tts-1" or "tts-1-hd"
  • input: string, max 4096 characters
  • voice: one of 8 presets
  • speed: 0.25–4.0
  • language: ISO code (optional)

Response Handling

A successful response returns the audio file directly in the body. Check the HTTP status code to confirm success. If the request fails, the response includes an error description and no charge is applied.

OpenAI SDK Integration

Sound wave illustration for: OpenAI SDK Integration

LMS Voice Core uses the same request shape as the OpenAI speech endpoint, allowing teams to leverage existing OpenAI SDKs with minimal configuration. By adjusting the base URL, your application can route synthesis requests directly to our infrastructure without requiring a custom client library.

This compatibility simplifies integration into established Python or Node.js pipelines used in enterprise learning management systems, ensuring consistent behavior across different development environments.

Base URL Configuration

Set the API base URL to https://api.playa1one.com/v1. This endpoint handles all synthesis requests using the standard JSON body structure, ensuring your existing code logic remains valid.

Client Initialization

Initialize the OpenAI client using your API key. Pass the custom base URL during instantiation. This directs all subsequent audio/speech calls to our servers while maintaining standard authentication headers.

SDK Compatibility

The official OpenAI SDKs work directly without modification. Since the request shape matches exactly, you can use the same library versions your team already manages, reducing dependency overhead.

  • Official OpenAI SDKs (Python, Node.js)
  • Standard JSON request body
  • No custom client required

Supported Audio Formats

Sound wave illustration for: Supported Audio Formats

The API supports MP3, WAV, OPUS, FLAC, and PCM output formats via the response_format parameter. This allows L&D teams to select the appropriate balance between file size and audio fidelity for their specific delivery channels.

Choosing the correct format ensures compatibility with existing Learning Management Systems and reduces unnecessary bandwidth usage during course distribution.

MP3 for Web Playback

MP3 is the recommended default for most web-based course players. It provides sufficient quality for voiceovers while maintaining small file sizes, ensuring fast loading times for learners on varying connection speeds.

  • Universal compatibility with HTML5 audio players
  • Optimal balance of quality and file size
  • Ideal for standard e-learning modules

WAV for High Quality

Select WAV when uncompressed, lossless audio is required for archival purposes or high-fidelity playback systems. This format preserves the full audio data without compression artifacts.

  • Lossless audio preservation
  • Suitable for professional audio review
  • Larger file sizes compared to MP3

OPUS and FLAC Options

OPUS offers efficient compression for modern web streams, while FLAC provides lossless compression for storage efficiency. PCM is also available as an uncompressed format. These formats allow teams to optimize storage costs without sacrificing audio integrity.

  • OPUS: High efficiency for web delivery
  • FLAC: Lossless compression for storage
  • Alternative to standard MP3/WAV workflows

Voice and Language Parameters

Sound wave illustration for: Voice and Language Parameters

Select from eight licensed voice presets optimized for corporate training and e-learning content. Each voice offers distinct tonal characteristics, from the warm clarity of Aria to the neutral delivery of Atlas, ensuring consistent audio quality across your course library. Every generated file carries an inaudible watermark that marks it as synthetic speech.

Voice Selection Presets

Choose from four female voices (Aria, Nova, Luna, Sage) and four male voices (Felix, Milo, Atlas, Orion). All voices support the full range of 23 languages, allowing for consistent character voice across diverse modules without requiring multiple voice purchases. Any voice can speak any of these languages.

  • 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

Language Code Override

The API guesses the language from the script, defaulting to English for Latin text. For non-English Latin-script content, explicitly set the language parameter to ensure accurate pronunciation. All 23 supported languages, including Arabic, Chinese, and Swahili, are available with any voice.

Speed Adjustment Range

Adjust playback speed between 0.25 and 4.0 to match presenter pacing or accommodate auditory processing needs in educational content. Standard speed (1.0) generates audio at roughly real-time, producing approximately 25 characters per second of audio.

Voice and Language Parameters

Rate Limits and Throttling

Sound wave illustration for: Rate Limits and Throttling

Rate limits are enforced per API key to ensure stable generation performance. The standard allowance is 60 requests per minute, which supports typical batch processing for course modules. New accounts start with 10 requests per minute before the first top-up.

60 Requests Per Minute

After initial top-ups, accounts operate at the full 60 RPM limit. This capacity is sufficient for most L&D teams generating audio for standard-length lessons.

Initial 10 RPM Limit

New accounts start with a 10 requests per minute limit. This applies until the first top-up is processed. It prevents abuse during the trial phase.

Queue Processing Behavior

Requests are processed sequentially. Under load, additional requests may wait in a queue. This ensures consistent audio quality but may increase total generation time for large batches.

Error Handling and Codes

Sound wave illustration for: Error Handling and Codes

The API returns standard HTTP status codes to indicate request success or failure. A 200 OK status confirms successful synthesis, while 4xx errors indicate client-side issues such as invalid authentication or missing parameters. 5xx errors are rare but may occur during temporary infrastructure spikes. There is no SLA or uptime guarantee.

Common HTTP Errors

401 Unauthorized: Check your Bearer token is correct. 429 Too Many Requests: You have exceeded the 60 requests per minute limit. 400 Bad Request: Ensure the input text does not exceed 4096 characters and the model is valid.

  • 401: Invalid or expired API key.
  • 400: Malformed JSON or invalid voice ID.
  • 429: Rate limit exceeded (60 req/min).

Retry Logic Recommendations

Implement exponential backoff for 429 and 5xx errors. Requests are processed sequentially; under load, a request may wait in a queue, causing temporary delays. Retry after 1-2 seconds for transient errors.

Character Limit Exceeded

The input field accepts up to 4096 characters per request. Text exceeding this limit must be split into chunks by your application before sending. Each chunk generates a separate audio file which must be joined client-side.

Advanced Usage Patterns

Sound wave illustration for: Advanced Usage Patterns

For large course modules, split input text into segments of up to 4096 characters. This ensures compliance with per-request limits while maintaining consistent audio quality across the entire lesson.

Parallel request handling can reduce total generation time for independent segments. However, requests are processed sequentially under load, so a queue may form during high demand. Monitor response times accordingly.

Generate audio files for each chunk individually, then join them into a single continuous file. This approach simplifies debugging and allows for precise length control in your LMS player.

Long Text Chunking Strategy

Split input text into segments of up to 4096 characters. This ensures compliance with per-request limits while maintaining consistent audio quality across the entire lesson.

  • Maximum 4096 characters per request
  • Spaces and punctuation count as characters
  • Use consistent voices for seamless playback

Parallel Request Handling

Submit multiple chunk requests concurrently to reduce total generation time. Be aware that requests are processed sequentially under load, so a queue may form.

Monitor response times and adjust concurrency levels based on your typical usage patterns to avoid excessive waiting periods.

Audio File Joining

Generate audio files for each chunk individually, then join them into a single continuous file. This approach simplifies debugging and allows for precise length control in your LMS player.

Ensure consistent voice settings across all chunks to maintain a uniform listening experience for your students.

  • Maintain consistent voice selection
  • Verify audio format compatibility
  • Test playback continuity before deployment

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Failed requests incur no charge, ensuring you pay only for successful audio synthesis.

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. W3C WAI: making audio and video accessible
  3. IETF RFC 7845: Ogg Opus
  4. LibriTTS-R corpus (OpenSLR 141)
  5. openai-python on GitHub
  6. Tether (USDT)
  7. TRON developer hub: TRC-20
  8. FFmpeg documentation
  9. Node.js documentation
  10. Creative Commons Attribution 4.0
  11. OpenAI API reference: create speech
  12. curl documentation

More on this site