Frequently asked questions
Which TTS API is best for courses?
Q: Which TTS API is suitable for courses? A: SpeakFlow is designed for no-code creators needing reliable, character-based pricing without complex infrastructure. It offers a simple cloud API that turns course scripts into audio files for LMS platforms. The pricing is transparent at $0.01 per 1,000 characters, making it easy to predict costs for your course content.
How does character pricing work?
Pricing 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 spend requirements, allowing you to pay only for what you generate.
Are the voices realistic?
Voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark marking it as synthetic speech. They are distinct from celebrity voices and do not include emotion tags or custom cloning capabilities.
Can I use this for commercial courses?
Yes, the API is suitable for commercial use. The voices are based on licensed recordings (LibriTTS-R CC BY 4.0 and LibriVox public domain). Input text is used only to produce audio and is not used for training. Generated audio is returned in the response and not stored.
What 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. Vietnamese, Indonesian, Thai, and others are not supported.
Is there a free trial?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days, allowing about 50,000 characters. Accounts created with email and password start without trial credit. You can top up your balance later using USDT on the TRON network to continue generating audio.
How do I integrate with my LMS?
Send text via a POST request to our endpoint. The request shape matches the OpenAI speech endpoint, so official OpenAI SDKs work by changing the base URL. You can also use plain HTTP. For longer texts, split them into parts of up to 4096 characters and join the audio files.
What audio formats are available?
You can choose from mp3, wav, opus, flac, and pcm formats. Specify the desired format in the response_format field of your request. This allows you to select the best format for your LMS platform, whether you need high quality or smaller file sizes.
Is my data used for training?
No. 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) solely for billing purposes. Your course content remains private.
How fast is the generation?
Typical speed is roughly real time, about 25 characters of text per second of generation. Short phrases take a few seconds. Requests are processed one after another, so under load, a request may wait in a queue. Longer texts are split and joined automatically.
Do I need coding skills?
Basic coding skills help, but the API is designed for no-code users. You can use the official OpenAI SDKs by changing the base URL to https://api.play66f.com/v1. We provide ready curl examples on the /get-api-key/ page. You can also use plain HTTP requests without complex infrastructure.
Can I clone voices?
No, we do not offer custom voice cloning. You cannot upload your own voice or design new voices. You must choose from the 8 preset voices (e.g., Aria, Nova, Felix, Milo). Custom cloning is not part of our current feature set.
What is the rate limit?
The limit is 60 requests per minute per key. Before the first top-up, the limit is 10 requests per minute. If you exceed the limit, requests may queue. Each request can handle up to 4096 characters of text. Adjust your generation speed accordingly.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20) only. The minimum amount is $5. Credits are added automatically within minutes after the transfer. We do not accept cards, PayPal, or subscriptions. Your balance does not expire, and you can top up anytime.
Character-based vs subscription pricing
Traditional subscriptions often charge for unused capacity or lock you into monthly tiers that don't match your course production cycles. Our API uses a simple character-based model: $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count, so your cost is directly tied to the script length.
This pay-per-use structure eliminates waste. You only pay for the audio you generate. Failed requests are free, ensuring you aren't charged for errors. This model is ideal for creators who produce content in bursts rather than at a steady daily rate.
Pay per use model
The API charges based on character count, not time or seat usage. With a balance that never expires, you can top up when needed. This approach aligns costs directly with your course output, making it easier to budget per module or lesson.
- $0.01 per 1,000 characters
- No monthly minimum spend
- No unused capacity fees
Subscription limitations
Subscriptions often require minimum commitments or charge for idle time. Our model removes these constraints. You start with a free trial of $0.50 credit (about 50,000 characters) valid for 7 days when signing in with Google, allowing you to test the quality before committing.
- No seat limits
- No idle time charges
- Cancel anytime
Cost predictability
Since pricing is per character, you can calculate exact costs before generation. Long texts are split into 4,000-character parts, keeping each request manageable. You can monitor usage via the dashboard, ensuring you stay within budget without surprise overages.
- Real-time usage dashboard
- Exact cost per request
- No hidden fees
Voice variety and quality
SpeakFlow provides eight distinct voice presets tailored for educational content, ranging from warm narrators to energetic presenters. This variety allows course creators to match the audio tone precisely to their subject matter and target audience.
Each voice is derived from licensed recordings in the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings. The API returns synthetic speech marked with an inaudible watermark, ensuring clear attribution while maintaining high audio fidelity for LMS platforms.
8 distinct voices
The API offers four female voices and four male voices, each with a specific character. Options include Aria (warm narrator), Nova (bright), Luna (soft storyteller), and Sage (calm instructor) for female tones. Male options include Felix (energetic), Milo (friendly), Atlas (neutral news), and Orion (deep documentary).
Creators can select the most appropriate voice for each module. This flexibility helps maintain listener engagement across long course series by varying the auditory experience without changing the core content.
- 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
Licensed recordings
All voices are based on the LibriTTS-R dataset, licensed under CC BY 4.0. Source material comes from LibriVox public-domain audiobook readings, ensuring a solid legal foundation for commercial use.
This approach avoids the complexity of custom voice cloning while providing high-quality, consistent synthetic speech. The inaudible watermark identifies the output as AI-generated without affecting the listening experience.
Clear narration
The engine is optimized for clarity, making it ideal for instructional content where pronunciation and pacing matter. With a generation speed of roughly 25 characters per second, audio is produced in near real-time for long texts.
Voices handle natural pauses and emphasis effectively, ensuring that educational material is easy to follow. This clarity supports better retention for students listening to course modules on LMS platforms.
Language support for global courses
A single voice engine speaks all supported languages with consistent quality. This allows you to produce courses in multiple languages without managing different voice models or negotiating separate contracts for each market.
The API supports 23 languages, covering major global markets. You can generate a full course curriculum in any combination of these languages using the same straightforward API call structure.
23 languages available
The service supports 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 most common educational markets without requiring specialized regional voices.
Each language is handled by the same 8 voice presets, ensuring tonal consistency across your entire course library. Whether you are teaching business English or technical German, the delivery style remains uniform.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Script-based guessing
If you do not specify a language, the system guesses it from the text script. Latin script text defaults to English, which works for many common use cases. This reduces configuration steps for simple English courses.
However, guessing is not perfect. If your text uses Latin characters but is in another language, the system may produce incorrect pronunciation or accent patterns. Relying on guessing is efficient but risks errors in multilingual content.
Explicit language setting
For reliable results, always set the language parameter with an ISO code. This ensures the engine uses the correct pronunciation rules for non-English Latin text, such as French or German. Explicit settings prevent awkward accents and mispronunciations.
This approach is critical for professional courses where clarity matters. By defining the language explicitly, you guarantee that the synthetic speech matches the intended linguistic context, avoiding confusion for learners.
Integration ease for no-code users
Integrating speech synthesis into your course workflow requires minimal coding. Our API uses standard JSON requests, ensuring compatibility with most no-code automation tools and LMS platforms without complex infrastructure.
You can leverage existing OpenAI SDKs by simply updating the base URL. This allows you to use familiar libraries for seamless audio generation directly within your existing development environment.
Standard JSON format
Send text and receive audio via a straightforward JSON body. The request structure mirrors industry standards, making it easy to map your course scripts to audio files using standard HTTP clients.
OpenAI SDK compatibility
Use official OpenAI SDKs by changing the base URL to our API endpoint. This ensures reliable, well-documented client libraries for Python, Node.js, and other languages without needing a custom SDK.
Simple API key auth
Authentication is handled via a single Bearer token in the header. Generate your key in your dashboard and pass it with each request. No OAuth flows or complex token management required.
Audio format flexibility
We support MP3, WAV, and Opus for broad compatibility. WAV offers uncompressed quality, while MP3 and Opus provide efficient compression. This ensures your audio files are lightweight and easy to manage within your course library.
MP3, WAV, Opus
Choose MP3 for small file sizes or WAV for lossless quality. Opus offers a modern balance of quality and compression. All formats are delivered directly via the API response.
FLAC and PCM options
For archival needs, use FLAC for lossless compression. PCM provides raw, uncompressed audio data. These formats are ideal if your LMS requires specific bit-depth or sample rate inputs without further processing.
Platform compatibility
The generated audio files are standard formats recognized by major LMS platforms. Moodle, Teachable, and Kajabi accept these files without conversion. This simplifies your workflow, allowing direct upload of API outputs.
Data privacy and retention
Your course scripts are used strictly to generate the audio file and are not used for model training. Once the audio is returned in the response, it is not stored on our servers. This ensures your intellectual property remains yours.
No training on data
Input text is processed solely for synthesis. We do not retain your scripts to improve our voice models or for other purposes. Your content stays private and is not ingested into our training datasets.
No audio storage
Generated audio files are delivered directly in the API response and are not saved on our infrastructure. You control where the audio is stored, whether in your LMS or your own cloud storage.
Billing metadata only
We keep only the necessary metadata for billing: request time, character count, and status. This data is used exclusively to calculate your usage charges and ensure accurate billing for your account.
Performance and limits
Text generation typically processes at roughly real-time speed, producing about 25 characters of text per second of audio for long scripts. Short phrases may take a few seconds to synthesize. Requests are processed sequentially, so high volume may cause brief queuing delays.
The API handles up to 60 requests per minute for each active API key. New accounts start with a lower limit of 10 requests per minute until the first top-up is completed. This ensures stable performance without requiring complex infrastructure management.
Real-time generation
Long texts are split into parts and joined automatically. Typical speed is roughly real-time (25 characters per second of generation). Short phrases take a few seconds.
Requests are processed one after another. Under load, a request may wait in a queue before synthesis begins.
60 requests per minute
Each API key is limited to 60 requests per minute. New accounts begin with 10 requests per minute.
The limit resets every minute. Upgrading your balance does not change the rate limit, ensuring consistent delivery.
4096 character limit
Each API request accepts up to 4096 characters of input text. Spaces and punctuation count toward this limit.
Split longer texts into chunks and concatenate the resulting audio files. This ensures consistent quality and avoids truncation.

Payment and top-up process
Top-ups are processed exclusively via USDT on the TRON network (TRC-20). This single-currency approach eliminates complex exchange rates or multi-currency fees, keeping your billing straightforward and predictable for your course business.
USDT on TRC-20 only
We accept only USDT on the TRON network (TRC-20). This simplifies your payment process by removing currency conversion fees and exchange rate variability, ensuring every dollar you send translates directly to your API credit.
Instant credit
Your balance updates automatically within minutes of your transfer confirming on the blockchain. There is no manual review or waiting period, so your course audio generation can resume immediately without administrative delay.
No minimum spend
You can top up any amount, with a minimum of $5. This flexibility allows you to scale your spending precisely according to your course production volume, without locking capital into large monthly subscriptions.
Support and documentation
We prioritize clear, self-service support for creators who prefer to solve issues independently. Our documentation provides practical, step-by-step guides tailored for no-code users, covering integration examples and troubleshooting common setup steps.
For direct assistance, we offer email support as our only channel. This ensures every query receives a thoughtful, written response without the noise of live chat windows.
Email support
All support inquiries are handled via email. We do not maintain a phone line or live chat widget, allowing us to focus on detailed, written responses that you can reference later.
- Direct email contact
- No wait times in queues
Clear documentation
Our guides are written for simplicity, avoiding complex jargon. You will find ready-to-use cURL examples and integration tips specifically designed for LMS platforms and no-code workflows.
No live chat
We do not offer real-time chat support. This keeps our operations simple and ensures you receive consistent, accurate information without the variability of live agents.
Watermarking and rights
Every audio file generated by SpeakFlow contains an inaudible watermark that clearly marks it as synthetic speech. This digital signature is embedded automatically during synthesis, allowing platforms and audiences to identify AI-generated narration without affecting playback quality or listener experience.
The synthetic nature is inherent to the licensed recordings from LibriVox and LibriTTS-R, ensuring transparency while maintaining professional audio standards for your educational content.
Inaudible watermark
Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This metadata is embedded directly into the audio stream, allowing your LMS or platform to identify the content as AI-generated without affecting playback quality or listener experience.
Synthetic speech mark
The watermark serves as a clear indicator of synthetic origin, ensuring transparency with your students. Since the voices are based on licensed recordings from LibriVox and LibriTTS-R, the synthetic mark aligns with the underlying data sources, providing a consistent and honest representation of your course content.
Commercial use allowed
You retain full rights to use the generated audio in your commercial online courses, LMS platforms, and marketing materials. The API output is ready for direct integration into your paid or free courses without additional licensing fees. You do not need to pay royalties per download or view, making it cost-effective for scaling your course library.
- No per-download royalties
- Ready for paid courses
- No additional licensing fees
Trial and onboarding
Getting started with SpeakFlow requires minimal friction. New accounts created via Google sign-in receive $0.50 of free trial credit, valid for seven days. This provides approximately 50,000 characters of generation capability, allowing you to test voice quality and integration without immediate payment details.
Email-based accounts start without this trial credit but can proceed to top-up instantly. The process is designed for creators who need to verify audio quality before committing to character-based billing.
$0.50 free credit
The trial credit covers roughly 50,000 characters. It is ideal for generating short sample clips to evaluate voice clarity and speed. The credit expires after seven days if unused.
Failed requests do not consume credit, ensuring you only pay for successful audio generation. This safety net allows for safe experimentation with different voices and speeds.
- Valid for 7 days
- Approx. 50,000 characters
- Covers basic testing
Google sign-in
Sign up directly via your Google account on the /get-api-key/ page. This method automatically activates the free trial credit. It is the fastest way to begin testing the API.
Accounts created with email and password do not receive the trial credit but can still access the full API features immediately after topping up.
Quick setup
Once signed in, you receive your API key immediately. Use the provided curl example or OpenAI SDK to send your first request. No complex infrastructure or long onboarding forms are required.
Top-ups are processed automatically via USDT on the TRON network. Credits appear in your balance within minutes, allowing you to scale from trial to production seamlessly.
Why choose this API
This API removes infrastructure guesswork for course creators. You send text and receive audio files ready for LMS upload. No complex pipelines or additional services to manage.
The pricing is straightforward: $10 per million characters. Failed requests are free. There are no monthly plans, seats, or minimum spends to complicate your budget.
Simplicity
Focus on your content, not the tech. The API handles the synthesis. Split long scripts into 4096-character parts and join the audio files easily.
- No custom infrastructure to maintain
- Direct audio file delivery
Transparent pricing
Pay only for what you use. Spaces and punctuation count as characters. You know exactly what each course costs before you start generating audio.
- $0.01 per 1,000 characters
- No hidden fees
Developer friendly
Uses standard JSON and OpenAI SDK compatibility. Change the base URL and use your key. Simple authentication with a single Bearer token.
- OpenAI SDK compatible
- Standard JSON format
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.
Sources and further reading
- Wikipedia
- IETF RFC 7845: Ogg Opus
- W3C WAI: making audio and video accessible
- LibriTTS-R corpus (OpenSLR 141)
- MDN: Web Speech API
- OpenAI API reference: create speech
- ISO 639 language codes
- Node.js documentation
- TRON developer hub: TRC-20
- openai-python on GitHub
- Creative Commons Attribution 4.0
- curl documentation
