Transparent Pricing for IVR Text-to-Speech API

By IVR TTS Audit editorial team · Updated 2026-11-19

This page details the exact cost structure for deploying natural-sounding voice menus via the IVR TTS API. We charge $0.01 per 1,000 characters, ensuring you pay only for what you use without minimum commitments. Ideal for startups scaling call center operations, our transparent model helps you forecast expenses for high-volume routing with precision.

You will find concrete cost examples for common IVR scenarios, including welcome menus and dynamic status updates. We also explain how USDT payments, rate limits, and refund policies affect your bottom line. Use this data to evaluate latency and character efficiency before integrating into your phone system.

Transparent Pricing for IVR Text-to-Speech API

Frequently asked questions

How much does 1 million characters cost?

The cost is $10 per 1 million characters, which equals $0.01 per 1,000 characters. This flat rate applies to all usage regardless of volume or voice selection.

Do spaces count towards the character limit?

Yes, spaces and punctuation count as characters. Each space, comma, or period is counted individually toward your 4,096-character request limit and your total character usage for billing.

Is there a minimum spend?

No, there is no minimum spend. You can top up with as little as $5 using USDT. There are also no monthly plans, seats, or minimum usage requirements.

How long does USDT top-up take?

Top-ups are credited automatically within minutes after the transfer is confirmed on the TRON network. We do not require manual invoice processing, so your balance updates quickly.

Can I pay with PayPal?

No, we do not accept PayPal. We only accept USDT on the TRON network (TRC-20) for top-ups. There are no cards or other payment methods available.

Do balances expire?

No, your balance does not expire. You can top up whenever needed, and the funds remain available for your IVR text-to-speech requests indefinitely without any time limit.

Are failed requests charged?

Failed requests are free. If synthesis fails, the charge is returned in full. You only pay for successful audio generation, ensuring you pay only for usable output.

Is there a free tier?

We offer a free trial of $0.50 credit (about 50,000 characters) valid for 7 days when signing in with Google. Email-based accounts start without trial credit.

How do I check my balance?

Log in to your account at /get-api-key/ to view your current balance, characters left, usage history, and a ready curl example. The dashboard provides usage data.

What is the cost of the trial?

The trial provides $0.50 of credit, allowing approximately 50,000 characters of speech generation. It is valid for 7 days and is granted automatically upon Google sign-in.

Can I use credit cards?

No, credit cards are not accepted. Payments are processed exclusively via USDT on the TRON network (TRC-20). This allows for direct, low-fee top-ups without intermediary banking fees.

Are there volume discounts?

No, there are no volume discounts. The price remains $0.01 per 1,000 characters regardless of how many characters you generate. There are no tiered pricing structures.

How are characters calculated?

Characters are calculated based on the input text length, including spaces and punctuation. Each character in your string counts toward the 4,096 limit and your billing total.

What happens if I run out of credit?

You cannot generate more audio until you top up. Top-ups via USDT are credited automatically within minutes. You can issue a new API key if needed while waiting.

Cost calculator

Estimated cost: $2.50

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

Core Pricing Structure

Sound wave illustration for: Core Pricing Structure

We charge $0.01 per 1,000 characters for text-to-speech synthesis, regardless of voice or language selected. This per-character model ensures predictable costs for high-volume IVR call routing, where message length varies significantly between short prompts and detailed hold instructions.

Per Character Cost

Per Character Cost

The standard rate applies to all generated audio files. You only pay for characters in the input text that are successfully converted; failed requests are free. Failed requests incur no charge, ensuring you do not pay for wasted cycles during peak usage.

  • Rate: $10 per 1 million characters

Space & Punctuation Count

Space & Punctuation Count

Every character in your input string contributes to the bill, including spaces, commas, periods, and quotation marks. When designing IVR menus, ensure concise phrasing to minimize character count without sacrificing clarity for callers.

Unified Model Pricing

Unified Model Pricing

Both the 'tts-1' and 'tts-1-hd' models use the same engine and pricing structure. There is no price difference for selecting higher fidelity; you can choose based on latency requirements without affecting your character consumption rate.

Cost Examples for IVR

Sound wave illustration for: Cost Examples for IVR

IVR systems require precise cost estimation to maintain profitability. Our pricing model charges $0.01 per 1,000 characters, including spaces and punctuation, ensuring predictable expenses for high-volume call routing.

Standard Welcome Menu

A typical 50-character greeting costs $0.0005 per call. With 10,000 monthly calls, this totals $0.50, making natural voice menus a cost-effective option.

Long Hold Messages

Hold messages often exceed 200 characters. At $0.01 per 1,000 characters, a 200-character message costs $0.002. Even with repeated loops, the cost remains negligible per user.

Dynamic Status Updates

Dynamic updates, such as estimated wait times, vary in length. A 100-character update costs $0.001. Generating these on-demand ensures accuracy without significant incremental costs.

Free Trial for Startups

Sound wave illustration for: Free Trial for Startups

Start testing our IVR TTS API immediately after signing up with Google. You receive $0.50 of credit, which covers approximately 50,000 characters. This allows you to validate voice quality and latency.

Accounts created using an email and password do not receive this initial trial credit. You must top up your balance before making your first API request. This ensures that your IVR system has funded capacity from the moment it goes live.

Google Sign-Up Credit

Sign in with Google to instantly receive $0.50 in credit. This amount translates to roughly 50,000 characters of synthesized speech, sufficient for testing welcome menus and hold messages.

  • Credit amount: $0.50
  • Approximate volume: 50,000 characters
  • Eligible for Google sign-up only

Email Sign-Up Terms

Users who register with an email address and password start with a zero balance. Unlike Google sign-ups, there is no automatic trial credit added to these accounts.

You must perform a top-up via USDT on the TRON network before your first API call. This requires no minimum initial spend, but the balance must be positive to process requests.

Trial Expiration Details

The trial credit is valid for 7 days from the moment of account creation. If you do not use the full $0.50 within this window, the remaining balance expires.

This time limit applies only to the initial trial credit. Any funds added via top-up do not expire and remain available for future IVR deployments.

Payment Methods

Sound wave illustration for: Payment Methods

IVR TTS Audit accepts payments exclusively via USDT on the TRON network (TRC-20). We avoid credit cards, PayPal, and traditional invoicing to keep overhead low for startups. This single-method approach minimizes administrative friction.

USDT on TRON Network

All top-ups are processed using USDT on the TRON (TRC-20) blockchain. This method provides near-instant settlement with minimal transaction fees compared to traditional payment gateways. You send the exact amount of USDT required, and our system credits your account automatically upon blockchain confirmation.

  • Accepts only USDT on the TRON network (TRC-20)
  • No credit cards, PayPal, or direct bank transfers
  • No VAT invoices or monthly subscription billing cycles

Minimum Top-Up Amount

The minimum top-up amount is $5. This low threshold allows startups to test the API with small call volumes without committing large sums. Your balance never expires, so you can top up only when needed, paying only for the characters you actually consume.

Auto-Credit Timing

Credits are added automatically within minutes of your transfer being confirmed on the TRON network. There is no manual review process or waiting period for business days. Once the transaction is visible, your API key is immediately funded and ready for IVR integration.

Payment Methods

Billing & Refunds

Sound wave illustration for: Billing & Refunds

We charge only for successful synthesis, ensuring your IVR budget isn’t drained by failed requests. If a voice generation fails, the cost is returned in full to your account balance immediately.

Failed Request Refunds

Failed requests are free. If synthesis fails, the charge is returned in full to your account balance.

Balance Expiration

Your prepaid balance never expires. You can top up via USDT on the TRON network at any time without worrying about losing funds due to account inactivity.

No Monthly Subscriptions

There are no monthly plans, seats, or minimum spend requirements. You pay exactly for the characters you generate, making it ideal for startups with variable call volume.

Rate Limits Impact on Cost

Sound wave illustration for: Rate Limits Impact on Cost

Rate limits directly influence your operational costs in high-volume IVR deployments. With a limit of 60 requests per minute per key, you must balance concurrent call routing against API throughput. Understanding these constraints helps prevent unnecessary queuing delays that affect caller experience.

When demand exceeds the 60-request threshold, requests are processed sequentially, potentially increasing latency. This queueing behavior impacts the perceived speed of your voice menu, especially during peak call times.

60 Requests per Minute

Each API key is capped at 60 requests per minute. This limit applies uniformly, regardless of model choice. For startups managing moderate call volumes, this throughput is usually sufficient for standard greeting loops.

New accounts start with a lower limit of 10 requests per minute until the first top-up is completed. This ensures fair usage before scaling up your IVR infrastructure.

  • Standard limit: 60 req/min per key
  • New account limit: 10 req/min until first top-up
  • Limit resets every 60 seconds

Queue Wait Times

When requests exceed the per-minute limit, they enter a processing queue. Requests are handled sequentially, meaning later requests wait for earlier ones to complete.

Typical synthesis speed is roughly real-time (about 25 characters per second). Short phrases may take a few seconds, but longer texts can take minutes. Queueing adds to this total latency, potentially affecting caller wait times in your IVR system.

  • Requests are processed sequentially when limits are exceeded
  • Latency increases with queue length
  • Longer texts take more time to synthesize

Concurrency Costs

To handle higher concurrency, you can issue additional API keys. Each key incurs its own rate limit, effectively multiplying your throughput capacity.

However, each key requires separate management. Monitor your usage per key to avoid hitting limits unexpectedly. This approach allows you to scale your IVR system linearly with your call volume.

  • Issue multiple keys for higher concurrency
  • Each key has its own 60 req/min limit
  • Manage keys to avoid unexpected limits

Comparison with Alternatives

Sound wave illustration for: Comparison with Alternatives

Pricing models vary significantly in IVR contexts. Competitors often charge per second of audio generated, which penalizes fast-talking voices or concise prompts. We charge per character, ensuring you only pay for the text you send, regardless of voice speed or duration.

Minimum charges also differ. Some providers bill for a minimum audio length even if your prompt is short. We apply no minimum charge per request; you pay exactly for the characters processed, making us efficient for short confirmation tones or brief hold messages.

Per-Second vs. Per-Character

Audio duration varies by voice speed and language. A per-second model creates unpredictable costs for fast-paced IVR menus. Our per-character model at $0.01 per 1,000 characters provides deterministic billing. You know the exact cost before sending the request, simplifying budget forecasts for high-volume call routing.

  • Predictable costs based on text length, not voice speed.
  • No penalty for concise prompts or fast-talking voices.
  • Direct correlation between input text and final bill.

Minimum Charge Differences

Many APIs impose a minimum charge for audio generation, even for short strings like "press 1." This inflates costs for frequent, short interactions typical in IVR systems. We charge strictly per character, so a 10-character prompt costs significantly less than a minimum-bill competitor, optimizing costs for high-frequency triggers.

  • No minimum charge per request or audio file.
  • Cost scales linearly with character count.
  • Ideal for frequent, short confirmation prompts.

Enterprise Contract Costs

Unlike enterprise providers requiring annual contracts, we operate on a pay-as-you-go basis. There are no monthly seat fees or volume discounts tied to long-term contracts. You retain full control over your budget with no hidden enterprise overhead or commitment penalties.

  • No annual contracts or minimum spend requirements.
  • No monthly seat fees or subscriptions.
  • Flexible scaling without contractual lock-in penalties.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. For longer scripts, split the text into parts, generate audio files, and join them programmatically.

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. ISO 639 language codes
  3. MDN: Web Speech API
  4. LibriTTS-R corpus (OpenSLR 141)
  5. Node.js documentation
  6. openai-node on GitHub
  7. IETF RFC 7845: Ogg Opus
  8. OpenAI API reference: create speech
  9. openai-python on GitHub
  10. LibriTTS-R paper (arXiv 2305.18802)
  11. TRON developer hub: TRC-20
  12. Creative Commons Attribution 4.0

More on this site