Text-to-Speech API for LMS & Audiobook Production

By Lectia editorial team · Updated 2026-11-19

Lectia helps product teams build accessible, long-form audiobooks and narrated courses without hiring voice actors. Our API turns your text content into natural-sounding audio at scale, supporting 8 distinct voices and 23 languages. Whether you are updating an LMS or producing a new series, you get consistent, high-quality narration that keeps learners engaged.

This page explains how to integrate our REST API into your workflow, from long-text splitting to format selection. You will find clear examples for e-learning, audiobooks, and podcast scripts, along with straightforward pricing and technical details. Get started with a free trial or explore the full documentation below.

Text-to-Speech API for LMS & Audiobook Production

Frequently asked questions

What is TTS API?

It is a cloud text-to-speech API where you send text and receive an audio file. The endpoint is POST https://api.f9999.info/v1/audio/speech with a JSON body. It uses the same request shape as the OpenAI speech endpoint, so official OpenAI SDKs work by changing the base_url to https://api.f9999.info/v1 and using your site key.

How does TTS compare to human narration?

TTS offers scalable, consistent narration without hiring voice actors. Generated files carry an inaudible watermark marking them as synthetic. While human narration offers unique emotional nuance, TTS provides uniform delivery at scale. Voices are based on licensed recordings from LibriVox public-domain audiobook readings, ensuring a natural, professional tone for your content.

What is the cost per character?

The cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full. There are no monthly plans, seats, or minimum spends. Balance does not expire, and you can top up with USDT on the TRON network.

Which voices are best for educational content?

For educational content, sage (calm, instructional) and luna (soft, storytelling) are ideal. Atlas (neutral, news) works well for factual delivery, while milo (friendly, conversational) suits interactive learning. You can adjust speed between 0.25 and 4.0 to match your course pace. All voices support 23 languages, allowing consistent narration across diverse student bases.

How many languages are supported?

We support 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. If the language parameter is not set, it is guessed from the script, defaulting to English for Latin text.

Can I use the API for long texts?

Yes, but you must split texts into parts of up to 4096 characters per request. You then join the resulting audio files. Typical speed is roughly real time, about 25 characters per second. Requests are processed sequentially, so under load, a request may wait in a queue. This ensures stable generation for long-form content.

What audio formats are available?

You can choose from mp3, wav, opus, flac, and pcm formats. These are specified in the response_format field of your JSON request body. The API returns the audio file directly in the response. No official SDK, mobile SDK, or WordPress plugin is provided; use the OpenAI SDK or plain HTTP requests.

Is there a free trial?

Yes, signing in with Google gives you $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. You can issue a new API key at any time, stopping the old one immediately. There are no subscriptions or minimum spends required to start.

How does the rate limit work?

The limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. Each request processes text up to 4096 characters. Requests are handled sequentially, so under heavy load, you may experience queuing delays. Failed requests are free.

Do I need to handle audio file storage?

Generated audio is returned in the response and not stored by our API. You are responsible for storing the audio files you receive. Input text is used only to produce the audio and is not used for training. Request metadata like time and status is kept for billing purposes only.

Can I adjust the speaking speed?

Yes, you can set the speed between 0.25 and 4.0 using the speed field in your request. This allows you to tailor the narration pace for different types of content, from slow, clear instructions to fast-paced summaries.

Are the voices cloned from real people?

Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. They are not cloned from specific real people or celebrities. Every generated file carries an inaudible watermark marking it as synthetic speech. We do not offer custom voice cloning or uploading your own voice.

How is the language detected?

If you do not set the language parameter, the system guesses it from the script. Latin-script text defaults to English. For non-English Latin-script text, you should explicitly set the language parameter to ensure accuracy. The API supports 23 specific languages; others like Vietnamese or Thai are not supported.

What happens if a request fails?

If synthesis fails, the charge is returned in full. Failed requests are free. You can retry the request or split your text differently. Input text is not stored after generation, and no training data is affected. Support is available via email if you encounter persistent issues with your API key or billing.

First request

curl

curl https://api.f9999.info/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

Why TTS for LMS?

Sound wave illustration for: Why TTS for LMS?

Replacing human voice actors for long-form content reduces production time from weeks to minutes. Our API handles bulk narration for entire course libraries, ensuring consistent audio quality across thousands of lessons without scheduling conflicts or studio booking delays.

Scalable Narration

Scalable Narration

Generate audio for up to 4096 characters per request. For longer texts, split and join seamlessly. Typical speed matches real-time narration, allowing you to scale course updates instantly without waiting for voice talent availability.

  • Process large course libraries in minutes, not weeks
  • Consistent voice across all modules and updates
  • No studio booking or talent scheduling required

Accessibility Compliance

Provide immediate audio access for diverse learners. Support 23 languages including English, Spanish, and Mandarin to meet global accessibility standards. Ensure your LMS content is inclusive and compliant without hiring multilingual narrators.

  • Support for 23 major languages out of the box
  • Instant audio generation for on-demand learning
  • Inclusive design for visual impairments and dyslexia

Cost Efficiency

Pay only $0.01 per 1,000 characters with no monthly fees. Avoid fixed salaries for voice actors. Failed requests are free, ensuring you only pay for successful audio generation. Start with a $0.50 free trial.

  • Pay-as-you-go pricing: $10 per 1M characters
  • No minimum spend or monthly commitments
  • Free trial credit included with Google sign-in

How It Works

Sound wave illustration for: How It Works

The API accepts standard JSON payloads via a single POST endpoint. You send your text and preferred voice settings, and the service returns the synthesized audio file directly in the response.

Simple API Integration

Integration mirrors the OpenAI speech endpoint structure, allowing you to use existing OpenAI SDKs by simply adjusting the base URL. Authentication is handled via a single Bearer token, making it easy to drop into your current LMS or content management workflow.

  • Standard JSON request body
  • Compatible with OpenAI SDKs
  • Single endpoint: POST /v1/audio/speech

Long Text Support

Each request supports up to 4096 characters. For longer courses or audiobooks, split your text into chunks and join the resulting audio files. This ensures consistent quality and avoids payload limits while keeping generation times predictable.

  • 4096 character limit per request
  • Split and join for longer content

Instant Audio Generation

Audio is returned in the response after synthesis completes. Short phrases take a few seconds, while longer texts generate at roughly real-time speed (25 characters per second). Failed requests incur no charge.

  • Direct audio file return
  • Roughly real-time generation speed

Voices for Learning

Sound wave illustration for: Voices for Learning

Lectia provides eight distinct voice presets designed for educational clarity. Whether you need a warm narrator for audiobooks or a calm instructor for courses, our library covers the spectrum. Each voice is grounded in licensed recordings, ensuring consistent, natural-sounding audio for long-form content.

8 Professional Presets

Our eight voices are engineered for distinct learning contexts. From the upbeat energy of Nova for short lessons to the deep, documentary tone of Orion for complex topics, you can match the voice to the subject matter. This variety helps maintain learner engagement across diverse course materials.

  • Aria: Warm, clear narrator ideal for fiction and stories.
  • Nova: Bright and upbeat, perfect for short, engaging lessons.
  • Luna: Soft and storytelling-focused, great for audiobooks.
  • Sage: Calm and instructional, suitable for training modules.
  • Felix: Energetic, best for promotional or intro content.
  • Milo: Friendly and conversational, ideal for direct instruction.
  • Atlas: Neutral tone, reliable for news or factual updates.
  • Orion: Deep and serious, suited for documentaries or history.

Clear Narration Styles

Clarity is critical for comprehension. Our voices are optimized for natural pacing, avoiding the robotic monotone common in older TTS systems. This ensures that complex educational concepts are delivered in a way that feels human and retains listener attention without causing fatigue during long study sessions.

Neutral & Warm Options

For sensitive or instructional content, neutral voices like Atlas provide a baseline of objectivity, while warm options like Aria and Luna create a supportive learning environment. These styles help reduce cognitive load, allowing students to focus on the material rather than the delivery method.

Supported Languages

Sound wave illustration for: Supported Languages

Lectia supports 23 languages, enabling global reach for your educational content. Our API handles diverse linguistic needs without requiring separate voice models for each region.

23 Languages Available

We support 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 covers the majority of major markets for online courses and digital audiobooks.

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

Multi-Language Courses

Create localized versions of your curriculum efficiently. Any of our 8 voices can speak any of the 23 supported languages, ensuring consistent brand voice across different language versions of your course material.

Language Guessing

The API automatically detects language from the text script. Latin script defaults to English if not specified, but you can set the language parameter for non-English Latin text. Languages like Vietnamese, Indonesian, Thai, and Ukrainian are not supported.

Pricing & Plans

Sound wave illustration for: Pricing & Plans

Our pricing is straightforward: $0.01 per 1,000 characters, including spaces and punctuation. This predictable cost structure helps product teams budget for large-scale LMS content or extended audiobook libraries without hidden fees. Failed requests are free, ensuring you only pay for successful audio generation.

You can generate audio instantly as needed. There are no monthly commitments or minimum spend requirements. Our transparent model scales with your content volume, making it ideal for courses that grow over time.

Pay Per Character

Charge is $10 per 1 million characters. Spaces and punctuation count. Failed requests are free.

  • $0.01 per 1,000 characters
  • Failed requests are free
  • No hidden fees

No Monthly Fees

No monthly plans, no seats, no minimum spend. Balance does not expire. Top-up via USDT (TRC-20) on TRON network, minimum $5.

No cards, no PayPal, no subscriptions, no invoices with VAT.

Free Trial Available

Sign in with Google to receive $0.50 credit (approx. 50,000 characters) valid for 7 days. Email/password accounts start without trial credit.

  • $0.50 credit
  • 7-day validity
  • Google sign-in required
Pricing & Plans

Technical Details

Sound wave illustration for: Technical Details

Our API endpoint matches the OpenAI speech structure, allowing you to swap in our base URL and use existing OpenAI SDKs without rewriting your integration logic. This compatibility simplifies testing and deployment for product teams already familiar with standard TTS workflows.

OpenAI Compatible

Use the official OpenAI SDKs by simply changing the base_url to https://api.f9999.info/v1. The request shape remains identical, supporting model, input, voice, and speed parameters out of the box.

Multiple Formats

Generate audio in mp3, wav, opus, flac, or pcm formats via the response_format parameter. This flexibility ensures compatibility with various LMS players and audiobook distribution pipelines.

Rate Limits

Each API key allows 60 requests per minute (10 before the first top-up). Long texts are handled by splitting input into 4096-character chunks and joining the resulting audio files seamlessly.

Use Cases

Sound wave illustration for: Use Cases

Turn static course content into engaging audio without hiring voice talent. Our API processes long texts by splitting them into manageable chunks, ensuring consistent narration for extensive e-learning modules and training libraries.

Generate natural-sounding audio files on demand. Whether you are producing textbook narrations or marketing content, the API delivers high-quality speech in multiple formats, ready for immediate integration into your learning management system.

E-Learning Courses

Replace expensive voice actor sessions with instant, scalable narration. Create consistent audio for thousands of lessons by simply sending your text to the API. The system handles the heavy lifting, delivering clear speech that supports accessibility standards.

  • Process long texts by splitting and joining audio segments
  • Maintain consistent voice across entire course catalogs
  • Supports 23 languages for global training content

Audiobooks

Produce narrated editions of your educational materials or published works at scale. With characters costing just $0.01 per 1,000, generating full books is significantly cheaper than traditional production. Each file includes an inaudible watermark to mark it as synthetic speech.

  • Cost-effective production for long-form content
  • 8 distinct voice presets for varied storytelling styles
  • No minimum spend or monthly fees

Podcast Scripts

Convert written scripts into ready-to-publish audio episodes. Use the API to generate voiceovers for your podcast content quickly. The natural-sounding output ensures your listeners receive high-quality audio without the logistical overhead of studio bookings.

  • Convert text scripts into MP3, WAV, or FLAC
  • Adjustable speed from 0.25x to 4.0x
  • Instant audio generation for rapid content turnaround

Integration

Sound wave illustration for: Integration

Integrate Lectia’s TTS API directly into your LMS or content delivery system using simple HTTP requests. The API follows the same request shape as the OpenAI speech endpoint, allowing you to change the base URL and use official OpenAI SDKs without rewriting your integration logic.

Webhooks are not supported; you will need to poll the API or implement your own event handling based on request status. This design keeps the service lightweight and focused on reliable audio generation without complex server-side event management.

REST API

Send a POST request to https://api.f9999.info/v1/audio/speech with your JSON body containing the model, input text, voice, and format. Authentication is handled via a Bearer token in the Authorization header, ensuring secure access to your account's credit balance.

  • Endpoint: POST /v1/audio/speech
  • Format: JSON body
  • Auth: Bearer token

SDK Support

Use the official OpenAI SDKs by updating the base_url to https://api.f9999.info/v1. This allows you to leverage familiar client libraries for Python, Node.js, and other languages, simplifying the integration process for your engineering team.

  • OpenAI SDK compatible
  • Update base_url only
  • No custom SDK needed

Webhooks

Webhooks are not available for this API. Since requests are processed sequentially and may queue under load, you should implement client-side polling or handle responses directly within your application flow to track generation status and download the resulting audio file.

Support

Sound wave illustration for: Support

Support is handled via email only; there is no phone number or live chat available. We respond to inquiries within one business day to help you resolve integration issues or billing questions.

Our documentation provides detailed endpoint references, code examples, and troubleshooting guides to help you integrate the API into your LMS or audiobook pipeline efficiently.

Email Support

Send your questions to [email protected]. Please include your API key (or key ID), a description of the issue, and relevant request logs or error messages for faster resolution.

Documentation

Visit /docs/ for complete API references, including request shapes, response formats, and SDK examples. The guides cover authentication, rate limits, and audio generation workflows.

  • API Reference with cURL examples
  • Integration Guides for Python and JavaScript
  • Error Code Definitions

FAQ

Common questions about character counting, voice selection, and payment methods are answered on the /pricing/ and /docs/ pages. If your question is not covered, email us directly.

  • How are characters counted?
  • Which voices support which languages?
  • How do I top up via USDT?

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Her pacing works well for quick tips, feature introductions, or engaging marketing-style course segments where energy is key.

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. openai-node on GitHub
  3. LibriTTS-R corpus (OpenSLR 141)
  4. W3C WAI: making audio and video accessible
  5. curl documentation
  6. Tether (USDT)
  7. OpenAI API reference: create speech
  8. LibriVox public-domain audiobooks
  9. LibriTTS-R paper (arXiv 2305.18802)
  10. MDN: Web Speech API
  11. ISO 639 language codes
  12. IETF RFC 7845: Ogg Opus

More on this site