Transparent Pricing for Text-to-Speech API

By SpeakFlow editorial team · Updated 2026-11-18

This page details the character-based billing for the SpeakFlow text-to-speech API, designed for no-code creators building course audio. You pay only for what you use, with a clear rate of $10 per million characters, making it easy to forecast costs for LMS platforms without complex infrastructure.

We cover trial credits, top-up methods via USDT, and concrete cost examples for short lessons or full series. Learn how failed requests are free, why there are no monthly subscriptions or seat limits, and how to manage your balance directly from the dashboard.

Transparent Pricing for Text-to-Speech API

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. There are no monthly fees, per-seat charges, or minimum spend requirements. You only pay for the characters you actually process, making it predictable for course script generation.

Do spaces count as characters?

Yes, spaces and punctuation count as characters. Every character in your input text, including spaces, is included in the character count for billing. This ensures accurate calculation of your usage. For example, a 4,000-character script will be charged for exactly 4,000 characters.

How do I pay with USDT?

Payments are made via USDT on the TRON network (TRC-20) only. Send your top-up amount to the address provided in your dashboard. The transfer is credited automatically within minutes after the transaction is confirmed on the blockchain. No other payment methods like cards or PayPal are supported.

Is the trial credit reusable?

No, the trial credit is not reusable. It provides $0.50 of credit, valid for 7 days, when you sign in with Google. Once used or expired, it cannot be restored. Accounts created with email and password start without this trial credit entirely.

What is the minimum top-up?

The minimum top-up amount is $5. You can add more USDT to your balance at any time. There is no upper limit, and you can top up as needed to ensure your course audio generation continues without interruption.

Do credits expire?

No, your balance does not expire. Once you top up your account, the credits remain available indefinitely. You can use them whenever you need to generate audio for your courses, without worrying about losing your funds due to time limits.

Are failed requests charged?

No, failed requests are free. If synthesis fails, the charge is returned in full. You only pay for successful audio generations. This ensures you are not charged for errors or issues that prevent the API from producing the final audio file.

Is there a monthly fee?

No, there is no monthly fee. You pay only for what you use based on character count. There are no subscriptions, seats, or minimum spend requirements. This model suits variable usage patterns common in online course production.

Can I get a refund?

Refunds are automatically applied for failed requests where the charge is returned in full. Your balance remains available for future use, and credits do not expire.

How do I check my balance?

You can check your balance on the /get-api-key/ page. The page displays your current balance, trial status, characters left, usage and a ready curl example. This real-time view helps you monitor spending as you generate audio for your courses.

Is there a volume discount?

No, there is no volume discount. The price is a flat $10 per 1 million characters regardless of how much you use. This simplicity means you do not need to negotiate tiers or track usage brackets for pricing.

Do I need a credit card?

No, you do not need a credit card. Payments are made exclusively via USDT on the TRON network. You can sign up with Google or email/password, but funding your account requires only a crypto wallet with TRC-20 USDT.

How long does top-up take?

Top-ups are credited automatically within minutes after the transfer is confirmed on the TRON blockchain. Once the transaction is processed, your balance updates immediately, allowing you to start generating audio without delay.

What currencies are supported?

Only USDT (TRC-20) is supported for top-ups. Prices are listed in USD, but payments are made in cryptocurrency. There are no other fiat currencies or payment methods like PayPal or credit cards available for this API.

Cost calculator

Estimated cost: $2.50

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

Character-based billing

Sound wave illustration for: Character-based billing

SpeakFlow charges $10 for every million characters processed, providing straightforward, predictable costs for your course audio production. This character-based billing model scales directly with your content volume, ensuring you only pay for the audio you actually generate.

$10 per 1 million characters

$10 per 1 million characters

Pricing is calculated per million characters, equivalent to $0.01 per 1,000 characters. This rate applies to all models, including both tts-1 and tts-1-hd, which use the same engine and pricing structure.

Spaces and punctuation count

Spaces and punctuation count

Every character in your input text contributes to the total count, including spaces, commas, and periods. When estimating costs for your course scripts, ensure you include all whitespace and punctuation in your character totals.

No minimum spend

There is no minimum spend requirement or monthly base fee. You can generate as little or as much audio as needed, making it ideal for creators who produce content irregularly or start with small batches of lessons.

Free trial for new accounts

Sound wave illustration for: Free trial for new accounts

New accounts created via Google sign-in receive an automatic $0.50 trial credit. This provides approximately 50,000 characters of audio generation, allowing you to test the API’s quality with a full lesson script before committing funds.

Email-based accounts do not receive this trial credit and start with a $0 balance. You must add funds via USDT to begin generating audio immediately.

$0.50 credit via Google sign-in

Upon signing in with Google, your account is instantly credited with $0.50. This amount covers roughly 50,000 characters of text-to-speech output.

This trial credit applies only to accounts created through the Google sign-in flow. It is automatically added to your balance without requiring a payment method on file.

  • Automatic credit upon Google authentication
  • Approximately 50,000 characters of generation time
  • No payment method required to start

Valid for 7 days

The trial credit remains active for seven days from the moment of account creation. If you do not use the credit within this window, it expires and cannot be reinstated.

Plan your testing schedule accordingly. You can generate multiple short clips or one longer script within this period to evaluate voice quality and integration speed.

  • 7-day validity window
  • Non-renewable
  • Expires automatically if unused

Email accounts start with $0

Accounts created using a standard email address and password begin with a zero balance. No trial credit is granted to these accounts.

You will need to perform a top-up using USDT on the TRON network before you can generate any audio. This ensures that all users start with a clear, known balance.

  • Zero initial balance
  • No automatic credit
  • Top-up required to generate audio

Top-up methods

Sound wave illustration for: Top-up methods

You can add funds to your account balance using USDT on the TRON network (TRC-20). This is the only payment method available for top-ups, allowing you to maintain a steady supply of credit for your course audio generation without waiting for bank transfers or subscription cycles.

There is a minimum top-up amount of $5. Once you send the USDT transfer, the credit is added to your account automatically within minutes, ensuring your API requests continue without interruption. You can issue a new API key at any time, and the old one stops immediately.

USDT on TRON network

We accept USDT transfers exclusively on the TRON network. This method is chosen for its speed and low transaction fees, making micro-top-ups practical for independent creators. Simply send your desired amount to the address provided in your dashboard.

  • Supports USDT (TRC-20) only
  • Compatible with most crypto wallets
  • No middlemen or payment processors

Minimum $5 top-up

The minimum amount you can add is $5. This lower threshold allows you to top up frequently as needed, rather than committing to larger monthly plans. Your balance does not expire, so you can accumulate credit over time.

  • Minimum deposit: $5 USD
  • No maximum limit
  • Credits never expire

Automatic credit within minutes

Once your TRC-20 transfer is confirmed on the blockchain, your balance is updated automatically. You do not need to wait for manual approval or send a receipt via email. Your dashboard reflects the new balance within minutes, ready for immediate use.

  • No manual approval needed
  • Updates within minutes
  • Immediate availability for API calls

Cost examples for courses

Sound wave illustration for: Cost examples for courses

Understanding audio production costs helps you budget for your course library. Because billing is strictly character-based, you can predict expenses precisely before generating any audio. This model eliminates surprises, allowing you to scale from a single lesson to a full curriculum without renegotiating contracts.

The API processes text sequentially, so longer texts may take slightly longer to generate but cost the same per character. This consistency makes it easy to estimate budgets for no-code LMS integrations.

Short lesson audio costs

A 4,000-character lesson script generates roughly 160 seconds of audio at normal speed, though total time varies by speed. At $0.01 per 1,000 characters, a standard 5-minute lesson script (approx. 12,000 characters) costs $0.12. Short phrases may take a few seconds to process due to queueing, but the cost remains fixed based on input length.

  • Example: 4,000 characters = $0.04
  • Includes spaces and punctuation
  • No hidden setup fees

Full course series costs

A comprehensive course with 20 lessons averaging 10,000 characters each totals 200,000 characters. This results in a total cost of $2.00 for the entire series. You can split longer texts into parts under 4,000 characters and join the audio files seamlessly, ensuring consistent quality across all modules.

  • 20 lessons × 10,000 chars = $2.00
  • Scalable to thousands of characters
  • No minimum spend per course

Multi-language expansion costs

Expanding your course to additional languages simply means sending the same text in different languages. Since any voice can speak any supported language, you do not pay extra for language switching. A 10,000-character script translated into five languages costs $0.25 total, making localization highly affordable.

  • All 23 languages supported
  • Same character rate
  • No extra language fees

Failed requests are free

Sound wave illustration for: Failed requests are free

Our billing logic ensures you never pay for audio that wasn’t successfully created. If synthesis fails for any reason, the character count is not deducted from your balance, and any pre-charged amount is refunded in full. This protects you when network issues or unexpected engine errors occur during generation.

You are only charged for requests that return a valid audio file. This means your costs strictly reflect the usable assets delivered to your LMS, eliminating waste from failed attempts or corrupted outputs.

Full refund on errors

When the API returns an error status, the request is marked as failed and no characters are consumed from your account. If a payment was already processed for that attempt, the credit is restored automatically.

This applies to all failure types, ensuring that temporary glitches do not impact your course production budget.

  • Zero cost for failed synthesis
  • Automatic balance restoration

No charge for bad inputs

If your request contains invalid parameters or exceeds limits, you are not billed. The system validates the input before processing, so you avoid paying for requests that would have failed anyway.

This is particularly useful for automated workflows where batch processing might occasionally include malformed text.

  • Invalid JSON structure returns zero charge
  • Exceeding 4096 characters returns an error and does not incur fees

Verify status codes

Always check the HTTP response code in your integration. A 200 OK confirms the audio is ready and the character count has been deducted. Any other code indicates a free request.

Your dashboard usage statistics reflect only successful generations, giving you an accurate view of your actual spending.

For debugging, log the response body to identify if the error was due to input format or server availability.

  • 200 OK = Charged
  • 4xx/5xx = Free
Failed requests are free

No monthly subscriptions

Sound wave illustration for: No monthly subscriptions

You pay only for what you use. There are no recurring monthly fees or automatic renewals to manage. Your balance covers each character processed, so your costs scale directly with your content output.

Pay only when you generate

Billing is triggered by successful API requests. If you create audio files for your course modules, you are charged only for those characters. Unused credit remains available for future lessons.

No seat limits

Your API key is not tied to a specific user. You can distribute the same key among your team or automated tools without paying extra for each person. This simplifies management for no-code creators.

No expiring credits

Unlike subscription models, your balance does not disappear at the end of a billing cycle. Funds remain in your account until you use them, making it easy to pause and resume course production.

Payment details

Sound wave illustration for: Payment details

We keep payment simple by accepting only one method: USDT on the TRON network. There are no credit cards, no PayPal, and no subscriptions. You top up with a minimum of $5, and the balance is credited automatically within minutes of your transfer.

Credits never expire, and you pay only for what you use. There is no monthly spend requirement or per-seat fee. Because we do not issue invoices with VAT, you will receive a simple transaction receipt via email for your records.

No credit cards

We do not store or process any credit card information. By removing payment processors, we eliminate monthly fees and chargeback complexities. This allows us to offer straightforward, character-based billing without hidden transaction costs.

You simply send USDT via the TRON network. Once the blockchain confirms your transaction, your account balance updates automatically, ready for immediate use.

  • Direct blockchain transfer
  • No third-party payment processor fees
  • Instant balance update

No PayPal

Unlike many SaaS platforms, we do not accept PayPal. This decision keeps our infrastructure lean and reduces currency conversion fees for international creators.

Using a single cryptocurrency standard simplifies the top-up process for developers who already manage API keys and server costs in crypto.

No VAT invoices

We do not issue invoices with VAT. You will receive a simple transaction receipt via email for your records.

This receipt contains the transaction hash, amount, and timestamp, providing sufficient proof of purchase for most accounting purposes without the overhead of formal tax documentation.

How it works

Sound wave illustration for: How it works

Generating audio for your LMS is a straightforward three-step process. You send your course script to our API, receive the synthesized audio file, and track your usage through the dashboard.

This workflow is designed for no-code creators who need reliability without complex infrastructure. Each step is handled automatically, allowing you to focus on content creation.

Send text via API

Use a standard HTTP POST request to send your text. The endpoint accepts JSON bodies with up to 4096 characters per call. You can specify the voice, format, and speed directly in the request.

For longer lessons, split the script into chunks and join the resulting audio files. This ensures consistent quality and avoids character limits.

  • Endpoint: POST /v1/audio/speech
  • Supports tts-1 and tts-1-hd models
  • Max 4096 characters per request

Receive audio file

The API returns the audio file in your chosen format (mp3, wav, opus, flac, or pcm). Processing takes roughly real-time speed, so a 10-minute lesson takes about 10 minutes to generate, plus potential queue time.

Failed requests are free, so you only pay for successful audio files. This protects your budget during testing.

Check usage dashboard

Access your account dashboard to view real-time usage statistics. You can see your remaining balance, characters consumed, and API key status.

The dashboard updates instantly, helping you monitor costs and plan your course audio production efficiently.

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.

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. FFmpeg documentation
  3. Tether (USDT)
  4. curl documentation
  5. OpenAI API reference: create speech
  6. LibriTTS-R paper (arXiv 2305.18802)
  7. TRON developer hub: TRC-20
  8. Creative Commons Attribution 4.0
  9. ISO 639 language codes
  10. Python documentation
  11. openai-node on GitHub
  12. LibriVox public-domain audiobooks

More on this site