Frequently asked questions
What is a cloud text to speech API?
It is a service that converts text into audio files via a simple HTTP request. You send text to our endpoint, and we return an audio file. This works with standard tools like the OpenAI SDK, allowing you to integrate speech generation directly into your course creation workflow without managing complex infrastructure.
How does the character billing work?
We charge $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. You pay only for successful audio generation, making it easy to predict costs for your course scripts based on character count.
Which voices are best for educational content?
Q: Which voices are suitable for educational content? A: Sage offers a calm, instructional tone ideal for lessons. Atlas provides a neutral, news-style voice suitable for clear information delivery. Luna is soft and storytelling-focused, while Aria is warm and clear for narrations. These presets are designed to keep learners engaged without distracting vocal styles.
Can I use the API for multiple courses?
Yes, the API is designed for scalability. You can generate audio for as many courses as needed using your single API key. There are no limits on the number of courses or projects you can process, allowing you to centralize your audio production across your entire content library.
What languages are supported?
We support 23 languages, including English, Spanish, French, German, Japanese, and Chinese. Any voice can speak any of these languages. If you do not specify a language, the system guesses it from the script, but setting it explicitly ensures accuracy for non-English Latin-script text.
Is there a limit on audio length?
Each API request accepts up to 4,096 characters of text. For longer scripts, you can split the text into parts, generate audio for each, and join the files. This approach ensures high-quality synthesis while allowing you to produce full-length course modules without character constraints.
Do I need coding skills to use this?
Basic coding knowledge helps, but it is not strictly required. Our API follows the standard OpenAI request shape, so you can use ready-made tools or simple scripts. We provide curl examples and documentation to help you integrate the service into your workflow, even with minimal technical experience.
How long does audio generation take?
Generation is roughly real-time, processing about 25 characters of text per second. Short phrases take a few seconds, while longer texts may take longer. Requests are processed sequentially, so high load may cause slight delays, but the output speed generally matches the audio duration.
Are the voices realistic?
Voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobooks. They sound natural and clear, suitable for professional course content. Each file includes an inaudible watermark indicating synthetic speech, ensuring transparency while maintaining high audio quality for your learners.
Can I upload my own voice?
No, we do not offer custom voice cloning or voice uploading. You choose from eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). These are fixed presets based on licensed recordings, providing consistent quality without the need for additional training or setup.
What happens if generation fails?
If synthesis fails, the charge is returned in full. You are not billed for unsuccessful requests. This ensures you only pay for audio that is successfully generated and delivered, protecting your budget when technical issues occur during the processing of your course scripts.
Is my course script data secure?
Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata (time, characters, status) for billing purposes, ensuring your content remains private and secure during processing.
Do you offer refunds?
Failed requests are automatically refunded in full. For other cases, refunds are handled via email support. We do not offer automatic refunds for successful generations, but you can contact us if there is a specific issue with your account or billing that requires review.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20). The minimum amount is $5, and credits are added automatically within minutes. We do not accept cards, PayPal, or subscriptions. Your balance does not expire, allowing you to manage your course audio production costs flexibly.
First request
curl
curl https://api.play66f.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.mp3Turn your course content into audio
Convert your course scripts into professional audio files with a simple API. Send text via JSON and receive the audio file directly, designed for seamless integration into LMS platforms.
Our API supports 23 languages, allowing you to localize content without complex infrastructure. Whether you need warm narration or clear instruction, we handle the generation so you can focus on curriculum development.
Script-to-audio workflow
Send your course text in a standard JSON POST request. The API processes the input and returns an audio file ready for your learning management system.
For longer lessons, texts are split into parts of up to 4096 characters and joined. You receive a single cohesive audio file.
- POST text to the /v1/audio/speech endpoint
- Receive MP3, WAV, FLAC, OPUS, or PCM files
- Automatic splitting for texts exceeding 4096 characters
Support for 23 languages
Generate content 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. Any voice preset can speak any supported language.
If the language field is omitted, the system guesses from the script. Latin text defaults to English, so explicitly set the language code for other Latin-script languages.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Simple character billing
Pay only for what you use: $10 per 1 million characters. Spaces and punctuation count toward the total. Failed requests are free, so you only pay for successful synthesis.
There are no monthly subscriptions or minimum spends. Your balance never expires, and you can top up with USDT (TRC-20) when needed.
8 voice presets for different teaching styles
Choose from eight distinct voice presets to match your teaching style, from warm narration to energetic promos. Each voice is based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings.
All voices support all 23 languages, allowing you to localize content without hiring new talent. Use the same voice across different languages or switch presets to keep your course engaging.
Female voices: Aria, Nova, Luna, Sage
Aria provides a warm, clear narrator tone ideal for general course introductions. Nova offers a bright, upbeat delivery for energetic lessons. Luna delivers a soft, storytelling style perfect for narrative-based modules. Sage ensures calm, instructional clarity for complex topics.
Male voices: Felix, Milo, Atlas, Orion
Felix brings an energetic, promo-ready voice for marketing modules. Milo offers a friendly, conversational tone for Q&A sections. Atlas provides a neutral, news-style delivery for factual content. Orion adds a deep, documentary feel for serious subjects.
Clear narration and instructional tones
Each voice is optimized for clarity, ensuring students can easily follow along with lecture notes and explanations. The synthetic watermark marks each file as AI-generated, maintaining transparency for your learners.
Easy integration for no-code users
Connect your course scripts to audio without writing complex code. Send a standard JSON payload with your text and voice preference, and receive an audio file ready for your LMS.
The API uses the same request structure as the OpenAI Speech endpoint. This means you can reuse existing code libraries and scripts with minimal adjustments.
If you run into issues, support is available via email.
Standard JSON request format
Send a simple POST request to the /v1/audio/speech endpoint. Include your model, input text, chosen voice, and desired audio format in the JSON body.
The system handles the conversion and returns the audio file directly in the response, ready for download or direct embedding in your course player.
- - Endpoint: POST /v1/audio/speech
- - Body: JSON with model, input, voice, and format
- - Response: Direct audio file
Works with OpenAI SDKs
Use the official OpenAI SDKs by pointing them to our base URL: https://api.play66f.com/v1.
This allows you to leverage familiar libraries in Python, Node.js, or other languages without learning a new client structure.
No custom SDKs are required; the standard HTTP client works just as well for simple integrations.
Support via email
For integration questions or technical issues, reach out to our support team by email.
We do not offer live chat or phone support, ensuring focused and documented assistance for your specific integration needs.
High-quality audio formats
SpeakFlow supports multiple audio formats to fit your LMS requirements. Choose MP3 for standard web playback, WAV for uncompressed clarity, or FLAC for lossless archiving. Each format balances quality and file size appropriately for course distribution.
MP3 for web players
MP3 is the most compatible format for web-based learning platforms. It offers small file sizes without sacrificing clarity, ensuring fast loading times for students. Use this format for standard course modules and quizzes.
WAV for high fidelity
WAV provides uncompressed audio. This format is ideal for premium courses where audio quality is a key selling point. It ensures the narrator’s tone remains crisp and clear.
FLAC for archiving
FLAC offers lossless compression, retaining full audio quality in a smaller file than WAV. It is perfect for storing master copies of your course content. Use FLAC when you need the highest fidelity for future edits or re-releases.
Pricing built for content volume
SpeakFlow charges strictly by character count, making costs predictable for large course libraries. You pay $10 per 1 million characters processed, with spaces and punctuation counting toward the total. This model scales directly with your content volume, eliminating wasted fees for unused capacity.
$10 per 1 million characters
Your billing reflects actual usage. At $0.01 per 1,000 characters, generating audio for a typical 2,000-character lesson costs just $0.02. This linear pricing ensures you only pay for the audio you actually produce, regardless of file length or voice selection.
No monthly subscriptions
There are no recurring fees, seat limits, or minimum spend requirements. Your balance does not expire, and you can top up with USDT (TRC-20) whenever needed. This structure suits creators who produce content irregularly or prefer to control cash flow without fixed overhead.
Free failed requests
If synthesis fails due to server issues, the charge is returned in full. You are never billed for audio that does not reach your endpoint, ensuring you only pay for successful audio generation.

Reliable generation speed
Generate audio at roughly real-time speed, processing approximately 25 characters of text per second. This consistent pace ensures that longer course modules convert to audio efficiently without unexpected delays for standard-length scripts.
Real-time processing
Synthesis begins immediately upon request submission. The engine processes text linearly, delivering audio files at a predictable rate that matches spoken word duration, allowing you to estimate generation time accurately based on script length.
Automatic text splitting
For scripts exceeding 4096 characters, the system automatically divides the input into manageable parts. Each segment is synthesized independently and then seamlessly joined into a single audio file, ensuring your entire lecture is delivered as one coherent file.
Queue management under load
Requests are processed sequentially. During periods of high traffic, additional requests may wait in a queue before synthesis begins. This ensures stable output quality without compromising the integrity of your audio files, though generation may take slightly longer than usual.
Data privacy for your courses
Your course scripts are processed solely to generate the requested audio file and are not retained for model training. This ensures your unique teaching content remains private and is not used to improve the TTS engine.
Text used only for generation
Input text is transmitted, synthesized, and returned in the response without being stored permanently. The generated audio is delivered directly to you and is not kept on our servers after the request completes.
No training on input data
We do not use your course content to train or refine the speech models. Your scripts remain distinct from the training data, preserving the integrity of your proprietary material.
Metadata kept for billing
We retain request metadata, including timestamps, character counts, and status codes, strictly for billing and usage verification. This limited data ensures accurate charging and helps diagnose any generation issues.
Start with a free trial
The free trial gives you $0.50 of credit, which covers approximately 50,000 characters. This allows you to generate full lesson audio files to test voice quality and integration without paying upfront.
$0.50 credit on sign-in
Your trial credit is available immediately after registration. You can use it to test any of the 8 voice presets or different audio formats.
Valid for 7 days
The trial credit expires 7 days after your account is created.
Google or email registration
You can sign up using your Google account or a standard email and password. Note that only Google sign-ins receive the free trial credit; email-only accounts start with a zero balance.
Technical limits to know
Before integrating, review these operational constraints to ensure your LMS workflow remains stable. Understanding these limits helps you design reliable automation scripts for your course audio generation.
4096 characters per request
Each API call accepts a maximum of 4096 characters, including spaces and punctuation. For longer lesson scripts, split the text into chunks and join the resulting audio files. Short phrases may take a few seconds to generate, while longer texts process at roughly real-time speed.
- Max 4096 characters per input
- Spaces and punctuation count
- Split and join for longer scripts
60 requests per minute
You are limited to 60 requests per minute per API key. New accounts start with 10 requests per minute until the first top-up. Requests are processed sequentially, so under heavy load, synthesis may queue briefly.
- 60 requests/minute after top-up
- 10 requests/minute for new accounts
- Sequential processing under load
No streaming or SSML
The API returns complete audio files, not streaming audio or WebSocket connections. It does not support SSML tags for pronunciation control or emotion modulation. Use the standard JSON format with OpenAI-compatible SDKs for integration.
- Returns complete audio files
- No streaming or WebSocket
- No SSML support
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This approach avoids the complexity of custom voice cloning while providing high-quality, consistent synthetic speech.
23 languages
Any voice speaks any of these languages.
