Frequently asked questions
How much does the API cost?
The API costs $10 per 1 million characters, which equals $0.01 per 1,000 characters. This flat rate applies to all models and voices, making it easy to predict expenses for your classroom audio projects.
Do spaces count as characters?
Yes, spaces and punctuation count as characters. When calculating your usage, every single character in your input text contributes to the total. This includes spaces between words, ensuring accurate billing based on the exact length of the text you send.
Is there a monthly fee?
No, there are no monthly fees. We do not offer subscriptions or seats. You simply pay for what you use. There is also no minimum spend required, so you can start small and scale your audio production as needed.
How does the free trial work?
You receive $0.50 of credit when you sign in with Google. This provides about 50,000 characters to test the API. If you create an account with an email and password, you start without this trial credit. It is a great way to verify quality.
Can I pay with credit card?
No, we do not accept credit cards or PayPal. Payments are made via USDT on the TRON network (TRC-20) only. This method allows for direct top-ups without the overhead of traditional payment processors, keeping our costs low for educators.
What is the minimum top-up?
The minimum top-up amount is $5. You can add funds to your balance at any time using USDT on the TRON network. Credits are credited automatically within minutes after the transfer is confirmed, allowing you to resume generating audio quickly.
How long does the trial last?
The free trial credit is valid for 7 days from the time you sign in with Google. After this period, any unused trial balance expires. You can then top up your account to continue generating audio for your teaching materials.
Do balances expire?
No, your balance does not expire. Once you top up your account with USDT, the credits remain available indefinitely. This is ideal for schools that may generate audio sporadically or need to preserve funds for future semesters without losing them.
Are failed requests charged?
No, failed requests are free. If synthesis fails, the charge is returned in full. This ensures you only pay for successfully generated audio files. You can test your text inputs without worrying about incurring costs for errors or processing issues.
Can I use my own wallet?
Yes, you can use your own TRC-20 wallet to send USDT. Simply transfer the desired amount to the address provided in your account dashboard. The system credits your balance automatically within minutes, allowing you to manage your payments directly via blockchain.
Is VAT included?
No, we do not issue invoices with VAT. Our pricing is straightforward: $10 per million characters. Since we do not handle traditional invoicing, VAT details are not applicable. This simplicity helps schools avoid administrative overhead when budgeting for API usage costs.
How do I check my balance?
You can check your balance on the /get-api-key/ page. The dashboard displays your current balance, trial status, characters left, and usage history. This view helps you monitor consumption and plan your audio generation projects effectively without unexpected charges.
Can I get an invoice?
No, we do not provide invoices with VAT. Payments are made via USDT on the TRON network. You can view your transaction history and balance on the /get-api-key/ page. This direct payment model simplifies accounting for individual teachers and small departments.
Is there a volume discount?
No, there is no volume discount. The price remains $10 per 1 million characters regardless of how much you use. There are no monthly plans or tiered rates. This consistent pricing makes budgeting predictable for schools of any size or usage level.
Cost calculator
Simple Per-Character Pricing
LumaSpeak charges $10 per million characters, which equals $0.01 per 1,000 characters. This flat rate applies regardless of the model selected, whether you choose tts-1 or tts-1-hd, as both use the same engine and pricing tier. Educators can budget accurately without worrying about variable model costs.
Cost Per 1,000 Characters
The base rate is $0.01 for every 1,000 characters of input text. This simplicity helps teachers estimate costs for entire chapters or lesson plans easily. Since the API processes text efficiently, you can generate audio for large documents without complex tier calculations.
- Rate: $0.01 per 1,000 characters
- Applies to both tts-1 and tts-1-hd models
- Predictable costs for classroom resources
Spaces Count as Characters
No Hidden Fees
Free Trial for New Accounts
Start creating audio content for your classroom immediately with a free trial. We want educators to experience the quality of LumaSpeak without any upfront commitment or credit card required.
The trial provides enough credit to generate approximately 50,000 characters of speech, allowing you to test voice presets and formats with real student materials.
Google Sign-In Bonus
When you sign up using your Google account on /get-api-key/, you instantly receive $0.50 in trial credit. This is the fastest way to begin generating audio for your lessons.
- Instant credit activation
- No payment method required
Email Sign-In Terms
If you prefer to create an account with just an email and password, you start with zero balance. You must top up via USDT to begin generating audio.
Trial Validity Period
The $0.50 trial credit is valid for 7 days from the moment of account creation. Unused credit expires after this period, so plan your testing accordingly.
Payment Methods for Schools
LumaSpeak uses USDT on the TRON network for school top-ups, keeping transactions simple and direct. There are no credit cards, PayPal accounts, or complex invoicing processes to manage for each purchase.
USDT on TRON Network
We accept only USDT on the TRON (TRC-20) network. This method ensures low transaction fees and fast processing, making it easy for schools to add funds without dealing with multiple payment gateways.
Minimum Top-Up Amount
The minimum top-up is $5. This low threshold allows teachers to start small and scale as needed, ensuring that schools can manage their TTS budget precisely without committing to large sums upfront.
Automatic Credit
Once your transfer is confirmed on the blockchain, credit is added automatically within minutes. You do not need to wait for manual verification or send an email to support to activate your funds.
Cost Examples for Classrooms
Understanding your budget starts with clear examples of how character counts translate to audio generation. Because spaces and punctuation count as characters, accurate estimation helps you plan resources effectively for your classroom materials.
Reading a Short Story
A standard 4,000-character story fits within one request limit. At $0.01 per 1,000 characters, generating this audio file costs just $0.04. This low cost allows you to create accessible versions of public domain texts or short assignments without worrying about high fees.
- Request limit: 4,096 characters per call
- Cost: ~$0.04 for a full short story
- Ideal for: Listening comprehension exercises
Generating a Lesson Plan
Lesson plans often range from 2,000 to 3,000 characters including formatting notes. Converting a detailed plan into an audio reference for teachers takes seconds. You can generate multiple voice versions (e.g., 'nova' for upbeat instructions or 'sage' for calm guidance) to test which works best for your team.
- Average length: 2,000–3,000 characters
- Speed: Roughly real time on long texts
- Voice options: Choose tone for clarity
Creating Audio Exams
An exam with 10 reading passages might total 15,000 characters. Splitting this into three API requests costs approximately $0.15. This is significantly cheaper than hiring voice actors for each unique test version, ensuring consistent audio quality across all student copies.
- Typical exam: ~15,000 characters
- Requests needed: ~3 splits
- Total cost: ~$0.15

No Monthly Subscriptions
Unlike traditional SaaS platforms that lock you into recurring billing cycles, LumaSpeak operates on a pure consumption model. You never pay for idle time or unused capacity, making it ideal for teachers with fluctuating usage needs throughout the academic year. There are no monthly subscriptions to manage, so your school’s budget remains flexible and predictable.
Pay Only When You Use
Our pricing is strictly per character, meaning you only incur costs when text is actually converted to audio. If you are not generating audio files, you are not paying. This eliminates the waste often associated with monthly seat licenses that go unused during summer breaks or holidays.
No Minimum Spend
Whether you need to convert a single paragraph for a quick classroom activity or a full textbook chapter, there is no minimum spending threshold. You can start with just a few cents if needed, allowing even small departments or individual teachers to experiment with TTS without financial risk.
Balance Does Not Expire
Any credit you add to your account via USDT on TRON remains valid indefinitely. You can top up once and use the balance over months or years, which is perfect for planning ahead for semester-long projects. Your funds are yours until you decide to use them for audio generation.
Failed Requests Are Free
When generating audio for classroom materials, occasional glitches happen. With LumaSpeak, you never pay for mistakes. If a synthesis request fails due to a server error or timeout, the charge is returned in full immediately.
Full Refund on Errors
Our billing system automatically detects failed requests and reverses the charge. You are only billed for successfully generated audio files, ensuring your school’s budget is spent on usable content.
No Charge for Failed Audio
Whether the issue is a temporary network hiccup or an internal processing error, the character count remains untouched. Your balance reflects only the audio you actually receive and can use in lessons.
Reliable Billing
We keep request metadata for transparency, but failed attempts do not clutter your usage logs with costs. This simple model means you can generate audio for essays or language drills with confidence, knowing errors won't inflate your bill.
Compare with Traditional Services
LumaSpeak offers a straightforward, character-based pricing model that eliminates the guesswork often found in traditional educational TTS platforms. By charging only $0.01 per 1,000 characters, we ensure that schools pay precisely for the content generated, whether it’s a short phonics exercise or a full chapter of a novel.
Unlike many competitors that lock features behind expensive tiered subscriptions, our API remains consistent regardless of volume. This transparency allows methodologists to budget accurately for the entire academic year without fearing hidden costs for additional voices or premium formats.
Lower Cost Per Character
Traditional services often charge premium rates for high-quality audio or limit character counts per month. Our flat rate of $10 per million characters ensures that even extensive reading libraries remain affordable. Spaces and punctuation count as characters, so your cost reflects the actual text processed without surprise fees.
- Flat rate: $0.01 per 1,000 characters
- No volume discounts needed; price stays consistent
- All formats (mp3, wav, opus, flac, pcm) included in base price
No Seat Limits
Most educational platforms charge per teacher or staff member, making it costly when multiple educators need access. With LumaSpeak, you get one API key for your team. Any teacher in your department can use the same key to generate audio for their classes without incurring additional per-user fees.
- One key for unlimited teachers
- No per-seat licensing fees
- Ideal for collaborative lesson planning
Transparent Usage
You can track every request through the dashboard, seeing exactly how many characters were processed and the resulting cost. There are no hidden tiers or obscured data usage fees. Failed requests are also free, so you only pay for successful audio generation, ensuring total billing clarity.
- Usage dashboard
- Clear character count tracking
- Zero charge for failed requests
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Selecting the right voice is essential for maintaining student engagement during language learning.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- openai-node on GitHub
- openai-python on GitHub
- ISO 639 language codes
- Node.js documentation
- W3C WAI: making audio and video accessible
- Creative Commons Attribution 4.0
- TRON developer hub: TRC-20
- OpenAI API reference: create speech
- Python documentation
- LibriTTS-R paper (arXiv 2305.18802)
- IETF RFC 7845: Ogg Opus
