Frequently asked questions
Is the TTS voice generator suitable for educational content?
Yes. Voices like Sage (calm, instructional) and Atlas (neutral, news) are designed for clear narration. The API accepts up to 4096 characters per request, allowing you to generate audio for lesson scripts efficiently. It removes the need for expensive voice actors or complex studio setups for online education.
How many languages are supported for course narration?
Voicera supports 23 languages, including English, Spanish, French, German, Chinese, Japanese, and Hindi. Any voice can speak any of these languages. If the language is not specified, it is guessed from the script, but setting it explicitly ensures accuracy for non-English Latin-script text.
Can I use different voices for different modules?
Yes. You can select from 8 distinct voice presets, including female voices like Aria and Luna, and male voices like Felix and Orion. Simply specify the desired voice parameter in your API request to switch between narrators for different course modules or lessons.
What audio formats are available for LMS integration?
The API supports MP3, WAV, OPUS, FLAC, and PCM formats. You can specify the response_format in your request body. MP3 and WAV are widely compatible with most Learning Management Systems, ensuring seamless integration of generated audio files into your course structure.
Does the API support long lesson scripts?
Yes. You can split texts into parts of up to 4096 characters and join the resulting audio files. This allows you to generate audio for lengthy lesson scripts by handling them in manageable chunks, ensuring high-quality synthesis for each segment.
Is the speech generation real-time or batch processed?
Requests are processed sequentially. Typical speed is roughly real-time on long texts (about 25 characters per second); short phrases take a few seconds. Under load, a request may wait in a queue.
Are the voices based on real human recordings?
Yes. Every voice is based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech, ensuring transparency about the audio's origin and nature.
Do I need technical skills to use the API?
The API uses a standard JSON body similar to OpenAI’s speech endpoint. You can use the official OpenAI SDKs by changing the base_url or send plain HTTP requests. A ready curl example is provided on the /get-api-key/ page, making it accessible for no-code users with basic integration steps.
How is pricing calculated for large courses?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, and there are no monthly plans or minimum spends. You only pay for the characters successfully processed in your course content.
Can I change my API key if it is compromised?
Yes. You can issue a new API key at any time from your account dashboard. The old key stops working immediately, ensuring your previous key cannot be used for further requests. This provides immediate security control without needing to contact support.
Is there a limit on characters per request?
Yes. Each API request accepts a maximum of 4096 characters in the input field. For longer lesson scripts, you must split the text into parts of this size and join the resulting audio files to create the complete narration for your course module.
Do I pay for failed audio generations?
No. If synthesis fails, the charge is returned in full. You only pay for successful audio generations. This ensures you are not billed for errors or issues during the processing of your course content, maintaining fair pricing for your usage.
Are the generated audio files stored on their servers?
No. Generated audio is returned in the response and not stored on Voicera’s servers. Input text is used only to produce the audio and is not used for training. Request metadata is kept for billing purposes, but the audio files themselves are transient.
Can I use the audio commercially in my courses?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. You can use the generated audio files in your commercial online courses and LMS content.
First request
curl
curl https://api.playe19.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 Course Creators Choose API Audio
API-driven audio generation allows course creators to maintain a consistent brand voice across all lessons without hiring multiple voice actors. By using a single TTS API, you ensure that every module sounds cohesive, regardless of who wrote the script.
Content updates become rapid. Instead of scheduling studio time for re-recordings, you simply update the text in your LMS and regenerate the audio. This keeps your course materials fresh and accurate with minimal effort.
Consistent Brand Voice
Using a dedicated API ensures uniformity. Whether you use Sage for calm instruction or Aria for warm narration, the same voice model applies to every lesson, creating a professional and recognizable learning experience.
- Single voice model across all modules
- Uniform tone for better retention
- No variation between lessons
Rapid Content Updates
Correcting an error or updating a statistic no longer requires a studio booking. You edit the text file and regenerate the audio file in seconds. This workflow keeps your course content accurate and up-to-date.
- Edit text, regenerate audio
- No studio scheduling needed
- Instant correction of errors
Global Reach with 23 Languages
Expand your audience by localizing content quickly. Our API supports 23 languages, including English, Spanish, French, Chinese, and Japanese. You can generate high-quality audio in any supported language without needing native speakers.
- 23 languages supported
- No native speaker required
- Easy localization workflow
Available Voices for Education
Voicera provides eight distinct voice presets designed to match various educational contexts. Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings.
Sage: Calm Instructional Narrator
Sage offers a calm, instructional tone ideal for complex theory explanations or step-by-step tutorials. Its steady pace helps learners retain information without distraction, making it suitable for long-form lessons where clarity is paramount.
- Ideal for detailed explanations
- Steady, clear pacing
- Reduces listener fatigue
Nova: Bright and Upbeat Guide
Nova brings a bright, energetic quality perfect for introductory modules or quick tips. This voice keeps engagement high, making it effective for short video summaries or motivating students to complete a module.
- High energy
- Engaging tone
- Great for short clips
Atlas: Neutral News Style for Lectures
Atlas delivers a neutral, authoritative sound suitable for academic lectures or factual content. Its balanced delivery ensures the focus remains on the material, providing a professional baseline for diverse educational topics.
- Neutral and authoritative
- Professional baseline
- Fact-focused delivery

Technical Integration for LMS
Voicera integrates seamlessly into existing LMS workflows by leveraging the standard OpenAI SDK. By simply adjusting the base_url to https://api.playe19.com/v1, developers can use familiar libraries without learning a new system. This compatibility ensures that scripts written for other platforms work immediately with Voicera’s endpoints, provided the base_url is adjusted.
The API accepts standard JSON bodies via POST /v1/audio/speech, making it easy to automate audio generation for course modules. You can specify models like tts-1 or tts-1-hd, select voices, and define output formats directly in your request, keeping your content pipeline consistent and predictable.
OpenAI SDK Compatibility
Use the official OpenAI SDKs by changing the base_url to https://api.playe19.com/v1. Your existing authentication headers and request structures remain valid, allowing for a drop-in replacement for other TTS providers. This reduces integration time for no-code and low-code LMS administrators.
Authentication is handled via a Bearer token in the Authorization header. One active key per account ensures secure access to your generated audio files. You can rotate keys instantly if needed, with the old key stopping immediately.
- Use official OpenAI SDKs with a simple
base_urlchange - Standard
Authorization: Bearerauthentication - Drop-in replacement for other TTS providers
Standard JSON API Format
Send text via a POST request to /v1/audio/speech with a JSON body. Fields include model, input, voice, response_format, and optional speed or language. The API returns the audio file directly in the response, ready for storage or playback.
Text input is limited to 4096 characters per request. For longer lessons, split the script into chunks and join the resulting audio files. This ensures consistent quality and manageable processing times, even for dense educational content.
- POST request to
/v1/audio/speech - JSON body with
model,input,voice,response_format - 4096 character limit per request
Multiple Audio Formats (MP3, WAV, FLAC)
Choose between mp3, wav, opus, flac, or pcm for your audio output. MP3 is ideal for web playback and smaller file sizes, while WAV and FLAC provide high-quality lossless audio for downloadable course materials. PCM offers uncompressed raw data for further processing.
Format selection allows you to optimize for bandwidth or quality based on your LMS requirements. All generated files contain an inaudible watermark to identify them as synthetic speech, ensuring transparency for your students.
- MP3 for efficient web streaming
- WAV and FLAC for high-quality downloads
- Opus and PCM for developer flexibility
Pricing for High-Volume Courses
Voicera charges $10 per million characters, which equals $0.01 per 1,000 characters. This straightforward metered billing ensures you only pay for the audio you actually generate. Spaces and punctuation count toward the character limit, so plan your scripts accordingly.
There are no monthly subscriptions, seats, or minimum spend requirements. You can scale your course production up or down without committing to a recurring fee. This model is ideal for LMS administrators managing diverse content libraries with varying audio needs.
$10 per Million Characters
The cost is fixed at $10 per million characters, or $0.01 per 1,000 characters. Failed requests are free: if synthesis fails, the charge is returned in full. A free trial provides $0.50 credit (approx. 50,000 characters) for 7 days when signing in with Google.
- $0.01 per 1,000 characters
- Failed requests are free
- $0.50 free trial for Google sign-ins
No Monthly Subscriptions
Voicera operates on a pay-as-you-go basis with no monthly plans or seats. Your balance does not expire, allowing you to top up only when needed. This eliminates the risk of paying for unused capacity during quiet periods.
Pay Only for Generated Audio
You pay strictly for successful audio generation. Request metadata is kept for billing, but input text is not used for training. Top-ups via USDT on the TRON network (TRC-20) are credited automatically within minutes after the transfer.
Supported Languages for Global Courses
Voicera supports 23 languages, allowing course creators to localize content without hiring separate voice actors for each region. The API automatically detects the language from the text script, though you can explicitly set the ISO code to ensure accuracy, especially for Latin-script texts that aren't English.
This flexibility ensures your educational materials reach a global audience with consistent audio quality, whether you are teaching basic concepts or advanced technical subjects in diverse linguistic markets.
English, Spanish, and French
These core languages are fully supported with all eight voice presets. You can generate lesson content in any of these languages using voices like Sage for calm instruction or Nova for upbeat engagement, ensuring your primary course materials sound natural and professional.
Asian Languages: Chinese, Japanese, Korean
Voicera provides native-sounding audio for Chinese, Japanese, and Korean, expanding your reach into major educational markets. Each language utilizes the full range of voice styles, allowing you to maintain a consistent brand voice across different linguistic regions.
European and Middle Eastern Options
Beyond the major languages, we support Arabic, Dutch, German, Greek, Hebrew, Hindi, Italian, Portuguese, Russian, Swedish, Turkish, Danish, Finnish, Norwegian, Polish, Malay, and Swahili. This extensive list allows you to create localized versions of your courses for a wide variety of learners.

Audio Quality and Format Options
Selecting the right audio format ensures your course files load efficiently while maintaining the clarity needed for learning. Voicera supports a range of output types to match your delivery method, from standard web playback to lossless archival storage.
MP3 for Web Streaming
MP3 is the default choice for most LMS platforms, offering a balance of file size and acceptable audio quality. Its compressed nature allows students to download lessons quickly, though the API does not support streaming.
- Universal compatibility with all major browsers and LMS players
- Optimal balance between file size and audio clarity
WAV and FLAC for High Quality
WAV provides uncompressed, high-fidelity audio ideal for audiobook-style courses where voice nuance is critical. FLAC offers lossless compression, reducing file size compared to WAV while preserving every detail of the synthesized speech for archival purposes.
- WAV for maximum compatibility with professional audio editors
- FLAC for significant storage savings without quality loss
Opus and PCM for Developers
Opus delivers high-quality audio at very low bitrates, suitable for mobile apps or bandwidth-constrained environments. PCM provides raw, uncompressed data for developers who need to process audio samples directly in their own pipelines or custom audio engines.
- Opus for efficient mobile streaming and low bandwidth
- PCM for raw data processing and custom pipelines
How It Works: Text to Audio
To generate audio for your course, send a POST request to the API endpoint with your script. The system accepts plain text up to 4,096 characters, allowing you to convert lesson segments directly into speech without complex configuration.
Send Text via POST Request
Structure your JSON body with the model, input text, and desired voice. The API handles the synthesis engine, converting your written lesson into a voice file that matches your instructional style.
- Supports up to 4,096 characters per request
- Simple JSON body structure
- Requires a valid API key
Receive Audio File Instantly
The API returns the generated audio file directly in the response. For longer lessons, split the text into parts and join the resulting audio files to maintain narrative continuity.
- Immediate response with audio data
- Supports MP3, WAV, FLAC, Opus, PCM
- Real-time processing for short phrases
Handle Errors Gracefully
If synthesis fails, the API returns an error status code. Failed requests are free, so no credit is deducted. Requests are processed one after another, so under load a request may wait in a queue.
Voice Selection Guide
Choosing the right voice ensures your course sounds professional and engaging. Voicera provides eight distinct presets, each tailored to specific instructional styles.
Select voices that match your content’s tone. Use warm narrators for storytelling, energetic voices for promos, or deep tones for documentaries.
Aria: Warm Narrator Style
Aria delivers a warm, clear narration ideal for storytelling modules or gentle introductions.
- Best for: Narrative lessons, soft intros.
Felix: Energetic Promo Voice
- Best for: Promos, quick updates.
Orion: Deep Documentary Tone
Orion provides a deep, authoritative voice suitable for documentary-style educational content.
- Best for: Documentaries, authoritative lectures.

Why Use an API for Course Audio?
Using an API transforms course audio from a manual production task into an automated workflow. Instead of scheduling studio time for every lesson update, you send your script to the endpoint and receive the audio file immediately. This eliminates the bottleneck of coordinating voice actors and engineers for minor content tweaks.
Automate Audio Generation
The API allows you to trigger synthesis directly from your content management system or LMS. By integrating the endpoint into your publishing pipeline, new lessons can generate audio files automatically upon publication. This ensures that your audio assets are always available the moment your text goes live.
- Trigger synthesis via standard HTTP requests
- Integrate directly with LMS publishing workflows
- Eliminate manual file upload steps
Scale Without Studio Costs
Traditional voice recording requires fixed overhead for studio rental and talent fees, regardless of volume. With Voicera, you pay only for the characters you process, starting at $10 per million characters. There are no monthly subscriptions or minimum spend requirements, making it affordable to produce audio for hundreds of lessons.
- No monthly subscriptions or seats
- Pay-per-use model ($0.01 per 1,000 characters)
- No minimum spend requirements
Keep Scripts and Audio in Sync
When you update a lesson script, regenerating the audio is as simple as sending the new text to the API. This ensures your audio always matches your current content without waiting for a voice actor’s availability. You maintain full control over the timing and accuracy of your educational material.
- Instant regeneration of audio files
- Precise alignment with updated text
- No waiting for talent schedules
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Launch your own courses and manage students easily with our intuitive platform.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- OpenAI API reference: create speech
- FFmpeg documentation
- LibriTTS-R paper (arXiv 2305.18802)
- curl documentation
- ISO 639 language codes
- LibriVox public-domain audiobooks
- W3C WAI: making audio and video accessible
- LibriTTS-R corpus (OpenSLR 141)
- Python documentation
- Creative Commons Attribution 4.0
- Node.js documentation
