Hindi Text-to-Speech API: Pricing, Voices & Localization Guide

By DubScript editorial team · Updated 2026-11-19

This page details the transparent pricing structure for the DubScript Text-to-Speech API, designed specifically for localization agencies managing high-volume dubbing projects. We charge $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. Both the tts-1 and tts-1-hd models operate at the same rate, ensuring consistent costs regardless of audio quality preferences.

You will find clear guidelines on payment methods, top-up procedures, and how to maximize your budget. Our system accepts USDT on the TRON network (TRC-20) with a $5 minimum top-up, credited automatically within minutes. There are no monthly plans, seat limits, or hidden fees, allowing you to scale your audio production efficiently without administrative overhead.

Hindi Text-to-Speech API: Pricing, Voices & Localization Guide

Frequently asked questions

Does the price differ between tts-1 and tts-1-hd?

No, both models use the same engine and price. You are charged $10 per 1 million characters regardless of whether you select tts-1 or tts-1-hd for your synthesis requests.

Are spaces and punctuation counted in the character limit?

Yes, spaces and punctuation count as characters. The billing rate is $0.01 per 1,000 characters, and every character in your input text contributes to this total usage calculation.

What happens if I exceed my balance?

The product facts do not specify the exact behavior when the balance reaches zero.

Is the free trial available for email-based accounts?

No. The $0.50 trial credit is given only when you sign in with Google. Accounts created with an email address and password start without any trial credit.

Can I use multiple API keys to increase rate limits?

No, rate limits apply per key. Each key is limited to 60 requests per minute (or 10 before the first top-up). Using multiple keys does not aggregate these limits.

Do I pay for requests that time out?

No. If synthesis fails, the charge is returned in full. You only pay for successful requests where the audio file is generated and delivered.

Is there a minimum spend requirement per month?

No. There are no monthly plans, no seats, and no minimum spend requirements. You pay only for the characters you consume, with no recurring costs.

How long does it take for USDT payments to reflect?

Payments are credited automatically within minutes after the transfer. We accept USDT on the TRON network (TRC-20) with a minimum top-up of $5.

What is the character limit per single API request?

Each request supports up to 4096 characters of input text. For longer texts, you must split the content into parts of this size and join the resulting audio files.

Which languages are supported besides Hindi?

We support 22 other languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.

Does the API support SSML for pronunciation control?

No, the API does not support SSML. It also lacks phoneme dictionaries, custom pronunciation lexicons, emotion tags, or voice cloning features.

Is there a rate limit on requests per minute?

Yes. Each API key is limited to 60 requests per minute. Before your first top-up, the limit is 10 requests per minute.

Can I use the OpenAI SDK with this API?

Yes. The request shape matches the OpenAI speech endpoint. You can use the official OpenAI SDK by changing the base_url to https://api.bbokk.info/v1 and using your site's key.

Are generated audio files stored on the server?

No. Generated audio is returned in the response and not stored. Only request metadata (time, characters, status) is kept for billing purposes.

Cost calculator

Estimated cost: $2.50

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

Standard Character-Based Pricing

Sound wave illustration for: Standard Character-Based Pricing

DubScript charges $0.01 per 1,000 characters for text-to-speech synthesis. This flat rate applies regardless of voice selection or language, making cost prediction straightforward for localization pipelines. You pay only for characters processed, ensuring transparency across all projects.

Spaces, punctuation, and standard Unicode characters all count toward the 1,000-character unit. For example, a 50,000-character script costs $0.50. This structure aligns with typical agency billing cycles, allowing precise budgeting for high-volume dubbing workflows without hidden multipliers.

$0.01 per 1,000 characters charged

$0.01 per 1,000 characters charged

The API bills in increments of 1,000 characters. Each request is evaluated on the total character count of the input text. This method ensures consistent pricing whether you are generating short notifications or full-length audiobooks.

Spaces and punctuation count as characters

Spaces and punctuation count as characters

Every character in your input string contributes to the bill. Commas, periods, line breaks, and spaces are not ignored. When splitting long texts for processing, ensure your segmentation logic accounts for these extra characters to avoid unexpected overages.

  • Include punctuation in your character count estimates
  • Line breaks count as single characters
  • Special Unicode characters may vary in count

Two models: tts-1 and tts-1-hd at same price

Two models: tts-1 and tts-1-hd at same price

Both tts-1 and tts-1-hd models are priced identically. The choice depends on your quality requirements rather than cost. Use tts-1 for standard dubbing needs and tts-1-hd when higher fidelity is necessary for broadcast-quality audio.

Free Trial for New Accounts

Sound wave illustration for: Free Trial for New Accounts

New accounts created via Google sign-in receive an instant $0.50 credit, providing approximately 50,000 characters of free usage. This trial allows localization teams to verify voice quality and API integration without immediate financial commitment.

The trial credit is valid for 7 days from the moment of account creation.

$0.50 credit for Google sign-ins

Upon authenticating with Google, your account is immediately credited with $0.50. This credit is applied to your balance automatically, allowing you to start generating audio files right away.

Approximately 50,000 characters of free usage

The $0.50 credit equates to roughly 50,000 characters, including spaces and punctuation. This volume is adequate for testing short scripts, verifying voice selection, or evaluating the API’s response time for typical dubbing tasks.

Valid for 7 days from account creation

Your trial balance expires 7 days after account registration. Unused credit is forfeited after this period, so plan your testing phase accordingly. Accounts created with email and password do not receive this trial credit.

Payment Methods and Top-Ups

Sound wave illustration for: Payment Methods and Top-Ups

Our payment infrastructure is built for simplicity and speed, utilizing cryptocurrency to bypass traditional banking delays and fees. We accept USDT on the TRON network (TRC-20) exclusively, ensuring that your credit is available when you need it for high-volume dubbing pipelines. This method eliminates the need for credit cards or PayPal accounts, streamlining the top-up process for agencies managing international projects.

The minimum top-up amount is $5. This lower barrier allows teams to test the API with small budgets before committing to larger volumes. Once you initiate a transfer, the system tracks the transaction and updates your account balance automatically, requiring no manual verification or support tickets to release your funds.

USDT on TRON network (TRC-20) accepted

We support USDT on the TRON network (TRC-20) as our sole payment method. This choice reduces transaction costs and avoids the variability of international wire fees. Agencies can send payments directly from their crypto wallets without linking bank details or exposing sensitive financial data to third-party processors.

  • Supports direct wallet-to-wallet transfers
  • No credit cards or PayPal required
  • Avoids international wire fees

Minimum top-up amount is $5

The minimum top-up amount is $5, which aligns with typical network transaction fees while keeping the entry point low for small teams. This amount provides sufficient credit to run initial tests or produce short audio clips. There are no subscription fees or monthly plans tied to your payment method; you simply add what you need.

  • Low entry barrier for testing
  • No recurring subscription fees
  • Flexible addition of funds

Credits auto-credit within minutes of transfer

Once your USDT transfer is confirmed on the blockchain, credits are automatically credited to your account within minutes. You do not need to wait for manual approval or send proof of payment. Your balance updates in real-time, allowing you to immediately start generating audio for your localization projects without administrative delays.

  • Automatic balance update
  • No manual verification needed
  • Funds available within minutes

No Hidden Fees or Subscriptions

Sound wave illustration for: No Hidden Fees or Subscriptions

We operate on a transparent, usage-based model. There are no monthly plans or seat limits, so you pay only for what you generate. This structure removes the risk of overpaying for idle capacity during quiet periods or underpaying during peak localization rushes.

No monthly plans or seat limits

Our platform charges per character, not per user or subscription tier. You can scale your team from one developer to dozens without incurring additional seat fees or breaking existing workflows. This flexibility supports agencies managing fluctuating project volumes without administrative overhead.

No credit cards or PayPal required

No VAT invoices available

No Hidden Fees or Subscriptions

Cost Efficiency for High Volume

Sound wave illustration for: Cost Efficiency for High Volume

The API is structured for localization agencies producing multilingual audio at scale. Each request accepts up to 4,096 characters, and you can split longer scripts into parts to join the resulting audio files seamlessly. This workflow supports the volume demands of dubbing pipelines without requiring complex infrastructure.

Ideal for bulk video dubbing projects

Agencies managing high-volume localization benefit from the straightforward character-based billing. Since costs are tied directly to text length, you can predict expenses precisely. The system processes requests sequentially, ensuring consistent pricing regardless of the voice model used.

  • Supports 23 languages, including Hindi, for diverse localization needs
  • Handles texts up to 4,096 characters per request
  • Sequential processing ensures predictable queue behavior under load

Pay only for successful requests

Your budget reflects actual production. If a synthesis fails for any reason, the charge is returned in full. You do not pay for wasted compute when errors occur, ensuring that every dollar spent results in a deliverable audio file.

Failed requests are refunded automatically

The refund mechanism is immediate and automatic. There is no need to submit support tickets for failed generation attempts. This reduces administrative overhead for teams processing thousands of lines daily, allowing you to focus on content rather than billing disputes.

Balance and Expiration

Sound wave illustration for: Balance and Expiration

Your prepaid credit remains available indefinitely, allowing you to pause and resume projects without financial loss. This structure suits agencies managing long-term localization pipelines where budget cycles may span months.

Balance does not expire over time

Unlike subscription models that reset monthly, your account balance persists until fully consumed. You can top up via USDT on TRON (TRC-20) whenever needed, with no deadline for using existing funds.

View current balance on dashboard

The /get-api-key/ dashboard displays your remaining credit and characters left in real time. This visibility helps you monitor spend against project milestones without waiting for end-of-period invoices.

Track characters used per request

Each API response reflects the character count processed, allowing precise budgeting. Since spaces and punctuation count as characters, you can accurately forecast costs for bulk dubbing tasks before submitting large volumes.

Example Cost Calculations

Sound wave illustration for: Example Cost Calculations

Understanding audio duration helps estimate production costs accurately. Since generation speed averages roughly real-time (25 characters per second), longer texts process efficiently. However, short phrases often require a few seconds regardless of length, affecting per-minute calculations differently than bulk dubbing.

The tts-1 and tts-1-hd models share the same character-based rate of $0.01 per 1,000 characters, including spaces and punctuation. This consistency simplifies budgeting for localization agencies managing high-volume projects.

Cost per minute of audio varies by speech rate

Adjusting the speed parameter (0.25–4.0) directly impacts audio length and cost efficiency. Faster speeds reduce duration, potentially lowering the effective cost per minute of final audio. Conversely, slower narration extends runtime, increasing the total character count processed over time.

Short phrases take longer to generate than long texts

While long texts generate at roughly real-time speed, short phrases may take a few seconds to process due to initialization overhead. Requests are processed sequentially, so under load, even brief requests may wait in a queue, impacting real-time delivery expectations.

Use the calculator to estimate project budgets

Input your script length and desired voice settings to estimate costs. Remember that failed requests are free, so only successful syntheses incur charges. This allows agencies to forecast expenses for multilingual dubbing pipelines with precision.

Track your balance and character usage directly on the dashboard. Top-ups via USDT on TRON (TRC-20) are credited automatically, ensuring your dubbing workflow continues without interruption.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. The gender balance allows for multi-character dialogue generation without relying on third-party voice cloning services.

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. Python documentation
  3. Tether (USDT)
  4. OpenAI API reference: create speech
  5. openai-python on GitHub
  6. Node.js documentation
  7. TRON developer hub: TRC-20
  8. openai-node on GitHub
  9. W3C WAI: making audio and video accessible
  10. ISO 639 language codes
  11. FFmpeg documentation
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site