Synthetic Speech API for Indie Developers

By Cloud TTS Indie editorial team · Updated 2026-11-18

Welcome to Cloud TTS Indie, a straightforward text-to-speech API built for indie developers and freelancers who need reliable audio without enterprise bloat. Here you will find the tools to integrate synthetic speech into your projects quickly, with transparent pricing and no hidden fees. Whether you are building a mobile app or a web service, our platform offers a simple way to turn text into natural-sounding audio files.

On this page, you can start generating speech immediately with a free $0.50 trial credit when you sign in with Google. We provide 8 distinct voices, support for 23 languages, and an OpenAI-compatible endpoint that works with your existing SDKs. Explore our documentation to see how easy it is to get started, or head to /get-api-key/ to claim your trial and see your API key in action.

Synthetic Speech API for Indie Developers

Frequently asked questions

What is the free text to speech API trial?

New accounts receive $0.50 of trial credit, which covers approximately 50,000 characters. This allows you to test the API’s quality and integration without any upfront commitment. The trial is valid for seven days from the time of sign-up, giving you ample time to evaluate the service.

How do I get started with the free trial?

Sign up on our /get-api-key/ page using your Google account. Upon signing in, you will automatically receive the $0.50 trial credit. You can then use the provided API key to make your first request via the standard OpenAI-compatible endpoint.

Do I need a credit card for the free trial?

No credit card is required to start the free trial. You only need to sign up with Google or create an account with an email and password. Payments for top-ups are processed via USDT on the TRON network, so no traditional banking details are needed.

What voices are available in the API?

We offer eight distinct voice presets: Aria, Nova, Luna, and Sage for female voices; Felix, Milo, Atlas, and Orion for male voices. These voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings, providing clear, natural-sounding speech for various use cases.

Can I use my own voice in the API?

No, we do not offer custom voice cloning or the ability to upload your own voice. The API uses eight preset voices derived from licensed recordings. If you need a specific voice, you must choose from the available presets like Aria, Felix, or Atlas.

Which languages does the API support?

The API supports 23 languages, including English, Spanish, French, German, Chinese, Japanese, Arabic, and Hindi. Any voice can speak any of these languages. If you do not specify a language, the system guesses it from the script, defaulting to English for Latin text.

Does the API support custom pronunciation?

No, the API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You can adjust the speed between 0.25 and 4.0, but you cannot fine-tune specific word pronunciations. For precise control, you may need to split your text and adjust the input manually.

How much does the API cost?

The API costs $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, and the charge is returned in full if synthesis fails. There are no monthly plans or hidden fees.

How is payment processed?

Payments are processed via USDT on the TRON network (TRC-20) only. There are no credit cards, PayPal, or invoices with VAT. The minimum top-up is $5, and credits are added automatically within minutes of your transfer. Your balance does not expire.

Is there a limit on characters per request?

Yes, each request can contain up to 4,096 characters of text. For longer texts, you should split the content into parts of this size and join the resulting audio files. This ensures efficient processing and avoids timeouts during synthesis.

What happens if a request fails?

If synthesis fails, the request is free, and the charge is returned in full. You can retry the request or split your text differently. This ensures you only pay for successful audio generation, protecting your budget from unexpected errors.

Do you offer a free tier or monthly plan?

We do not offer a free tier (always-on) or monthly plans. You pay only for what you use, with a minimum top-up of $5. There are no seats, no minimum spend, and no subscriptions. Your balance remains available until you use it.

Is my input text used for training models?

No, your input text is used solely to produce the audio and is not used for training models. The generated audio is returned in the response and not stored. We keep request metadata like time and status for billing purposes only.

How long does the trial credit last?

The $0.50 trial credit is valid for seven days from the time you sign in with Google. If you create an account with email and password, you start without trial credit. Ensure you test the API within this window to avoid losing the credit.

First request

curl

curl https://api.play35bd.com/v1/audio/speech \
  -H "Authorization: Bearer $TTS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
  --output hello.mp3

Start with a free trial

Sound wave illustration for: Start with a free trial

Start testing our text-to-speech API immediately by signing in with Google. You receive a $0.50 credit, enough for roughly 50,000 characters of synthetic speech, without entering any payment details.

This trial is valid for 7 days, giving you ample time to evaluate voice quality, language support, and integration speed for your indie project.

No credit card is required to begin. If you decide to continue after the trial, you can top up using USDT on the TRON network with a minimum of $5 and no monthly commitments.

$0.50 credit on Google sign-in

$0.50 credit on Google sign-in

Upon signing up via Google on /get-api-key/, your account is instantly credited with $0.50. This allows you to generate approximately 50,000 characters of audio to test the API's capabilities thoroughly.

The credit applies to all models and voices, letting you experiment with different formats like MP3 or WAV without hesitation.

  • Instant credit upon Google sign-in
  • Approximately 50,000 characters of audio
  • Works with all voices and models

7-day validity for testing

Your trial credit remains active for 7 days from the moment of sign-up. This window is designed to give indie developers and freelancers enough time to integrate the API, test edge cases, and validate audio quality for their specific use case.

If you don't use the credit within this period, it expires, but your account remains active for future top-ups.

  • Valid for 7 days
  • Time to test integration
  • No rush to decide

No credit card required

We keep the barrier to entry low. You can start generating speech without linking a credit card or providing billing information. This eliminates the risk of unexpected charges while you explore the platform.

When you're ready to scale, you can add funds via USDT (TRC-20) with a minimum top-up of just $5.

  • No credit card needed
  • Start testing immediately
  • Low barrier to entry

8 distinct voices for any project

Sound wave illustration for: 8 distinct voices for any project

Choosing the right tone is critical for indie apps, and we’ve curated eight distinct presets to fit any context. Whether you need a warm narrator or a deep documentary voice, our library covers the spectrum without requiring complex engineering.

Each voice is a preset based on licensed recordings, providing clear and natural-sounding speech. You can mix and match styles across your project to keep content engaging.

Female voices: Aria, Nova, Luna, Sage

Aria offers a warm, clear narration style perfect for storytelling or educational content. Nova brings a bright, upbeat energy ideal for social media clips or quick updates. Luna provides a soft, comforting tone for bedtime stories or calm interfaces. Sage delivers a calm, instructional voice suited for tutorials or guides.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional

Male voices: Felix, Milo, Atlas, Orion

Felix is energetic and promotional, great for ads or announcements. Milo offers a friendly, conversational style that feels natural for chatbots or customer service. Atlas provides a neutral, news-ready tone for straightforward information delivery. Orion delivers a deep, documentary-style voice for serious or cinematic content.

  • Felix: Energetic, promo
  • Milo: Friendly, conversational
  • Atlas: Neutral, news
  • Orion: Deep, documentary

Licensed from LibriVox and LibriTTS-R

All voices are based on licensed recordings from the LibriTTS-R dataset (CC BY 4.0) and readings from LibriVox public-domain audiobooks. This foundation ensures high-quality, natural-speech characteristics without the need for extensive training data.

Every generated audio file includes an inaudible watermark, clearly marking it as synthetic speech while maintaining the natural flow of licensed human recordings.

Support for 23 languages

Sound wave illustration for: Support for 23 languages

You can generate speech in 23 languages, with any voice capable of speaking any of them. This flexibility lets you build global apps without managing separate voice models for each region.

If you omit the language field, the system guesses it from the script. Latin script defaults to English, so you must explicitly set the language for other Latin-based languages like Spanish or French to ensure accurate pronunciation.

Major languages: English, Spanish, French, German

These core languages are fully supported with all eight voices. You can mix languages in a single project by specifying the ISO code for each request.

For non-English Latin script, always set the language parameter. Without it, the API assumes English, which may cause pronunciation errors for other languages.

  • English
  • Spanish
  • French
  • German

Asian languages: Chinese, Japanese, Korean

Support includes Simplified Chinese, Japanese, and Korean. Each voice adapts to the phonetic structure of these languages, providing natural-sounding results for diverse markets.

These languages do not default to English, so the API detects them automatically from the script. However, explicit language codes ensure consistent behavior across different request types.

  • Chinese
  • Japanese
  • Korean

Other supported: Arabic, Hindi, Russian, Turkish

Beyond the major languages, we support Arabic, Hindi, Russian, and Turkish, along with Danish, Dutch, Finnish, Greek, Hebrew, Italian, Malay, Norwegian, Polish, Portuguese, Swahili, Swedish, and more.

Each voice handles the unique rhythms and scripts of these languages. You can test any voice with any language to find the fit for your content.

  • Arabic
  • Hindi
  • Russian
  • Turkish

Simple integration

Sound wave illustration for: Simple integration

Connecting your project to our TTS API is straightforward. We use the same request shape as the OpenAI speech endpoint, meaning you don’t need to learn a new syntax or install a custom library. Just point your code to our API base URL and use your API key.

This approach lets you leverage familiar tools while avoiding the overhead of enterprise-grade contracts. You get reliable audio generation with minimal code changes, perfect for indie developers who value simplicity and speed.

OpenAI-compatible endpoint

Our API mimics the standard OpenAI structure, so you can swap the base URL to https://api.play35bd.com/v1 and keep using your existing logic. This compatibility ensures a smooth transition without rewriting your integration code.

Works with official OpenAI SDKs

Since the request shape is identical, the official OpenAI SDKs work out of the box. You can use your preferred language client, update the base_url, and start generating speech immediately. This saves you time on custom HTTP client setup.

JSON body with standard fields

Send text via a simple JSON body with fields like model, input, voice, and response_format. You can also adjust speed between 0.25 and 4.0. It’s a clean, standard interface that fits right into any modern web app or backend service.

You don’t need to manage complex parameters. Just provide the text and voice, and we handle the rest. The response returns the audio file directly, ready to be played or stored.

  • Use standard JSON fields like model, input, and voice
  • Adjust speed from 0.25x to 4.0x easily
  • No custom library required; use existing HTTP clients

Transparent pricing

Sound wave illustration for: Transparent pricing

For indie developers who need to keep costs predictable, our pricing is straightforward and based entirely on usage. You pay only for the text you successfully convert, with no monthly subscriptions, seat fees, or hidden charges. The standard rate is $10 per 1 million characters, which breaks down to just $0.01 per 1,000 characters.

$10 per 1 million characters

This flat rate applies to all requests, regardless of the model chosen. Both "tts-1" and "tts-1-hd" use the same engine and price, so you can upgrade quality without changing your budget expectations.

$0.01 per 1,000 characters

Spaces and punctuation count as characters, making it easy to estimate costs before sending a request. For example, a 4,000-character script costs $0.04. This clarity helps freelancers budget accurately without guessing hidden fees.

Failed requests are free

If synthesis fails for any reason, the charge is returned in full. You never pay for audio that wasn't delivered, ensuring you only spend on successful generations.

Transparent pricing

Flexible payment with USDT

Sound wave illustration for: Flexible payment with USDT

Top up your balance using USDT on the TRON network (TRC-20). This method keeps things simple and direct for indie developers who prefer crypto over traditional banking hassles.

Credits appear automatically within minutes of your transfer, so you can keep coding without waiting for manual approvals or long settlement periods.

USDT on TRON network (TRC-20)

We accept USDT on the TRON network because it offers fast transactions and low fees. This ensures your credits arrive quickly without unnecessary costs eating into your budget.

  • Fast confirmation times
  • Low transaction fees
  • Direct balance update

Minimum $5 top-up

The minimum top-up amount is just $5. This low entry point makes it easy to test the API or top up small amounts as needed without locking away large sums.

No subscriptions or monthly plans

There are no monthly subscriptions or recurring fees. You pay only for what you use, and your balance never expires. This model suits freelancers and indie projects with variable audio generation needs.

Audio formats and speed

Sound wave illustration for: Audio formats and speed

Choose the audio format that fits your app’s bandwidth and compatibility needs. We support MP3, WAV, Opus, FLAC, and PCM, giving you full control over file size and quality without extra conversion steps.

Formats: MP3, WAV, Opus, FLAC, PCM

Select the output that matches your player or storage constraints. MP3 offers small file sizes for web use, while WAV and FLAC provide lossless quality for archival or high-fidelity projects. Opus and PCM handle compressed and raw data needs efficiently.

  • MP3 for web and mobile efficiency
  • WAV and FLAC for lossless quality
  • Opus and PCM for raw data handling

Speed control: 0.25x to 4.0x

Adjust the playback speed to match your content’s pace. From slow, clear narration at 0.25x to rapid, energetic delivery at 4.0x, you can fine-tune the voice to suit audiobooks, tutorials, or quick alerts.

Real-time generation on long texts

For longer scripts, the API processes requests sequentially. While short phrases take a few seconds, longer texts generate at roughly real-time speed (about 25 characters per second). You can split text into 4096-character chunks and join the resulting audio files seamlessly.

No hidden limits or fees

Sound wave illustration for: No hidden limits or fees

You might expect enterprise-grade limits, but we keep things simple. There are no monthly plans, no seat limits, and no hidden fees. Just a straightforward API that scales with your usage, whether you’re building a small prototype or a busy production app.

The only hard limit is 60 requests per minute per key. If you need more, you can issue a new key instantly. Your balance never expires, so you can top up when it suits you without losing any credits.

60 requests per minute per key

Each API key handles 60 requests per minute. Before your first top-up, this limit drops to 10 requests per minute, which is plenty for testing your integration without wasting credits.

If you hit the limit, requests are processed one after another. For longer texts, generation takes roughly real-time (25 characters per second), so you won’t burn through your quota too quickly.

  • - 60 requests/min after first top-up - 10 requests/min for new accounts - Queue handles burst traffic

4096 characters per request

Each API call accepts up to 4,096 characters of input. For longer texts, split them into chunks and join the resulting audio files. This keeps each request lightweight and predictable.

Spaces and punctuation count toward the limit. Short phrases may take a few seconds to generate, while long texts process at roughly real-time speed.

Balance never expires

Your credit balance does not expire. Top up with USDT when needed, and the funds are available immediately. No subscriptions, no auto-renewals, no surprises.

Failed requests are free, so you only pay for successful audio generation. Your balance reflects exactly what you’ve used, nothing more.

Data privacy and licensing

Sound wave illustration for: Data privacy and licensing

We keep your workflow lean. Your input text is processed solely to generate the audio file and is not used for model training. We retain only request metadata—timestamp, character count, and status—necessary for accurate billing.

Input text not used for training

Unlike some services, we do not consume your creative content to improve our base models. Once the audio is synthesized, the original text is not retained for analysis or training purposes, keeping your data isolated to your immediate use.

Audio returned in response, not stored

The generated audio file is delivered directly in the API response and is not stored on our servers afterward. This ensures that your final output remains transient and secure, reducing data retention risks for indie projects with sensitive content.

Inaudible watermark on synthetic speech

Every audio file generated includes an inaudible digital watermark. This marks the clip as synthetic speech, helping you maintain transparency if you distribute the audio publicly, without affecting the listening experience or requiring additional metadata management.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence.

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. W3C WAI: making audio and video accessible
  3. Creative Commons Attribution 4.0
  4. ISO 639 language codes
  5. Node.js documentation
  6. LibriTTS-R corpus (OpenSLR 141)
  7. Python documentation
  8. FFmpeg documentation
  9. IETF RFC 7845: Ogg Opus
  10. TRON developer hub: TRC-20
  11. curl documentation
  12. Tether (USDT)

More on this site