TTS API for Indie Developers: A Practical Guide

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

This guide explains how Cloud TTS Indie helps freelancers and indie developers generate high-quality speech without the complexity of enterprise platforms. We cover everything from integrating our OpenAI-compatible API to understanding our transparent, character-based pricing model.

You will learn how to select from eight licensed voices, manage 23 languages, and handle rate limits effectively. Whether you are building a simple prototype or scaling a medium-sized project, this page provides the practical details you need to start generating audio immediately.

TTS API for Indie Developers: A Practical Guide

Frequently asked questions

What makes this API good for indie developers?

We offer straightforward OpenAI-compatible endpoints, so you can use existing SDKs by simply changing the base URL. There is no enterprise bloat, just a reliable API for audio generation. Pricing is transparent at $0.01 per 1,000 characters, with no monthly plans or hidden fees, making it easy to budget for small projects.

Is this API suitable for freelancers?

Yes, our platform is designed for freelancers who need reliable audio without complex contracts. You can start with a free trial credit and top up via USDT on TRON (TRC-20). The simple integration and predictable per-character pricing allow you to manage costs effectively while delivering high-quality synthetic speech to your clients.

How does it compare to other TTS APIs?

We do not claim to be the best or fastest. We provide a compatible endpoint that works with official OpenAI SDKs. Our pricing is strictly per character used, with no minimum spend or seats. We focus on transparency and simplicity rather than enterprise features or brand affiliation.

Is it easy to integrate?

Integration is simple because we mimic the OpenAI speech endpoint. You just change the base URL to https://api.play35bd.com/v1 and use the official OpenAI SDKs or plain HTTP. Send a POST request with your text and voice, and receive an audio file. No custom SDKs or complex setups required.

What languages are supported?

We support 23 languages, including English, Spanish, German, French, Japanese, and Chinese. Any voice can speak any of these languages. If you do not specify a language, it is guessed from the script, but we recommend setting it explicitly for non-English Latin text to ensure accuracy.

Are there any hidden costs?

No, there are no hidden costs. You pay $0.01 per 1,000 characters, including spaces and punctuation. Failed requests are free, and charges are returned in full if synthesis fails. There are no monthly plans, no seats, and no minimum spend. Balance does not expire, and you only pay for what you use.

Does it support voice cloning?

No, we do not support custom voice cloning. You cannot upload your own voice or design a custom voice. We offer eight presets based on licensed recordings from LibriTTS-R and LibriVox. Each generated file includes an inaudible watermark to mark it as synthetic speech.

Is there a free trial?

Yes, signing in with Google gives you $0.50 of credit, valid for 7 days. Accounts created with email and password start without trial credit. This allows you to test the API before topping up. Top-ups are processed automatically via USDT on the TRON network.

How is payment handled?

Payments are handled via USDT on the TRON network (TRC-20) only. There are no cards, PayPal, or invoices. The minimum top-up is $5, and credits are added automatically within minutes. Your balance does not expire, and you can issue a new API key at any time if needed.

What is the character limit?

Each request can process up to 4,096 characters of text. For longer texts, you should split them into parts and join the resulting audio files. Spaces and punctuation count toward the character limit. Typical generation speed is roughly real-time, with short phrases taking a few seconds.

Is there a rate limit?

Yes, each API key is limited to 60 requests per minute. Before your first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so under load, a request may wait in a queue. This ensures fair usage across all independent developers.

Does it support SSML?

No, we do not support SSML. You cannot use phoneme dictionaries or custom pronunciation lexicons. The API accepts plain text input and generates audio based on the selected voice and speed settings. If you need precise control, you may need to split text and adjust parameters manually.

Is there a mobile SDK?

No, we do not provide a dedicated mobile SDK. You can use the official OpenAI SDKs by changing the base URL, or use plain HTTP requests. This approach allows you to integrate the API into any mobile app that supports standard network calls without needing a specific mobile library.

How is customer support handled?

Support is handled by email only. There is no phone number, live chat, or SLA. We do not offer enterprise contracts or on-premise installations. For technical issues or billing questions, you can reach out via the contact page, and we will respond via email.

Criteria for indie developers

Sound wave illustration for: Criteria for indie developers

Indie developers and freelancers need tools that work without friction. Our API is designed for straightforward integration, allowing you to generate audio with minimal code overhead.

We focus on what matters: clear costs and a lightweight architecture that doesn’t force you into complex enterprise workflows or hidden fees.

Simple API integration

Start generating audio immediately with a standard JSON request. The endpoint mirrors the OpenAI speech format, so you can use familiar SDKs by simply changing the base URL.

No complex setup is required. Send text, receive an audio file, and move on to building your product.

  • Standard JSON request body
  • Compatible with OpenAI SDKs
  • Minimal code overhead

Transparent pricing

Pay only for what you use. There are no monthly subscriptions or minimum spend requirements. The cost is fixed at $10 per million characters, making budgeting predictable for any project size.

Failed requests are free, so you never pay for errors. This model suits freelancers who need reliable audio generation without enterprise bloat.

No enterprise bloat

We skip the unnecessary features that drive up costs and complexity. There are no SLAs, no dedicated support lines, and no complex contracts.

This simplicity allows you to integrate quickly and focus on your core product, whether you are building a prototype or scaling a small application.

Why our API stands out

Sound wave illustration for: Why our API stands out

We built our API to feel familiar. It uses the same request shape as OpenAI’s speech endpoint, so you can switch by just changing the base_url to https://api.play35bd.com/v1 and using your key. The official OpenAI SDKs work by changing the base_url, saving you from learning a new client library.

OpenAI-compatible endpoint

Integration takes minutes, not days. Send a standard JSON payload with model, input, and voice to receive an audio file. Whether you use Python, JavaScript, or plain cURL, the workflow remains consistent and predictable.

  • Same request shape as OpenAI’s /v1/audio/speech
  • Works with official OpenAI SDKs
  • Supports MP3, WAV, OPUS, FLAC, and PCM

USDT payment for global devs

Pay with USDT on the TRON network (TRC-20). This avoids regional banking restrictions and credit card fees. Top-ups start at $5 and are credited automatically within minutes, ensuring you never face a surprise invoice or VAT complication.

  • TRC-20 USDT only
  • Minimum top-up: $5
  • Automatic credit within minutes

No monthly subscriptions

You only pay for what you use. There are no seats, no minimum spend, and no recurring monthly plans. Your balance does not expire, so you can pause projects without losing your credit. It is pure usage-based pricing.

  • Pay-as-you-go model
  • No monthly subscriptions
  • Balance never expires

Voice selection

Sound wave illustration for: Voice selection

Choosing the right voice is critical for setting the tone of your project. We offer eight distinct presets designed to cover a wide range of narrative styles, from warm narration to energetic promos.

Each voice is a preset with a distinct character, making it easy to find a match for your content.

8 curated voices

We provide eight specific voice presets, each with a distinct character. Female options include Aria for warm narration, Nova for upbeat energy, Luna for soft storytelling, and Sage for calm instruction. Male voices offer Felix for energetic promos, Milo for friendly conversation, Atlas for neutral news delivery, and Orion for deep documentary styles.

You can select any voice regardless of the language you are using, allowing for flexible casting across your projects.

  • Aria: warm, clear narrator
  • Nova: bright, upbeat
  • Luna: soft, storytelling
  • Sage: calm, instructional
  • Felix: energetic, promo
  • Milo: friendly, conversational

Clear distinction between male/female

The voices are clearly categorized by gender to help you quickly narrow down your options. This distinction helps maintain consistency in character voices for dialogue-heavy projects or e-learning modules.

You can mix and match these voices within a single application or across different projects as needed.

Licensed from public domain sources

All voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. This ensures high-quality source material while keeping licensing straightforward for indie developers.

Every generated audio file includes an inaudible watermark to identify it as synthetic speech, adding a layer of transparency for your end users.

Language support

Sound wave illustration for: Language support

Cloud TTS Indie supports 23 languages, from Arabic to Turkish. Any voice can speak any supported language, giving you flexibility for global projects.

If the API misidentifies your text, you can explicitly set the language parameter. Without it, Latin script defaults to English, so always specify for non-English Latin text.

23 languages supported

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

This covers most major markets indie developers target. Each voice handles all listed languages natively.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Auto-detection with override

The API guesses the language from the script if you omit the language field. Latin text defaults to English.

Set language to any ISO code from our list to override detection. This ensures accuracy for mixed-language or less common Latin-script texts like Danish or Malay.

No support for Vietnamese or Thai

Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, and other languages not listed are not supported. Check the full list before integrating to avoid unexpected errors.

Pricing transparency

Sound wave illustration for: Pricing transparency

Pricing is straightforward: $10 per million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, with the charge returned in full if synthesis fails. This flat rate applies to all models, so you never need to choose between quality tiers for cost reasons.

$10 per million characters

Each request processes up to 4096 characters. For longer texts, split the input and join the audio files. The cost scales linearly with usage, making it easy to predict expenses for e-learning modules or podcast series without complex tier calculations.

  • Flat rate of $10 per 1M characters
  • Spaces and punctuation count as characters
  • Failed requests are free

No hidden fees

There are no monthly subscriptions, no per-seat charges, and no minimum spend. You only pay for what you generate. The balance does not expire, so you can top up when convenient. Support is email-only, so there are no extra fees for premium help channels.

  • No monthly subscriptions
  • No per-seat charges
  • No minimum spend

Free trial available

Sign in with Google to receive $0.50 of credit, valid for 7 days. This covers about 50,000 characters, enough to test multiple voices and languages. Accounts created with email and password start without trial credit. Top-ups are made via USDT on TRON, credited automatically within minutes.

  • $0.50 credit with Google sign-in
  • Valid for 7 days
  • Covers ~50,000 characters

Integration ease

Sound wave illustration for: Integration ease

Integration is straightforward because we use the same endpoint structure as the OpenAI speech API. You can swap your base URL and start generating audio immediately without learning a new protocol. This compatibility means you can use existing OpenAI SDKs or simple HTTP requests, reducing the learning curve for indie developers and freelancers who want to focus on their product rather than infrastructure.

We provide ready-to-use cURL examples in the docs to help you test the API quickly. The request body is simple: specify the model, input text, voice, and output format. This simplicity ensures that even complex TTS logic can be implemented with minimal code overhead, fitting seamlessly into indie projects without enterprise bloat.

Works with OpenAI SDK

Our API endpoint mirrors the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by simply changing the base URL to https://api.play35bd.com/v1. This means you can leverage familiar libraries and tools you already know, making integration faster and more reliable for indie developers who prefer established ecosystems.

You can pass your API key as a Bearer token in the Authorization header. The request shape is identical, so any code written for OpenAI’s speech endpoint will work here with minimal adjustment. This compatibility reduces development time and allows you to switch providers or test alternatives without rewriting your core audio generation logic.

  • - Compatible with OpenAI SDKs by changing base_url
  • - Standard Bearer token authentication
  • - No custom client library required

cURL examples provided

We provide cURL examples in the docs for common use cases, making it easy to test the API directly from your terminal or scripts. These examples demonstrate the exact JSON structure needed for successful requests, helping you verify your setup before integrating into your application.

You can copy and paste these examples to quickly generate audio files. The examples cover common use cases like generating MP3 or WAV files, adjusting speed, and selecting specific voices. This transparency helps you understand the API’s behavior and troubleshoot issues without reading through extensive documentation.

  • - Copy-paste ready cURL commands
  • - Covers all 8 voices and 5 formats
  • - Demonstrates speed and language parameters

JSON standard format

Requests are sent as standard JSON bodies, making it easy to integrate with any programming language that supports JSON. You specify the model (tts-1 or tts-1-hd), the input text, the voice, and the desired response format. This simplicity ensures that your code remains clean and readable, even when handling complex TTS logic.

The JSON structure is minimal, requiring only the essential fields for audio generation. Optional fields like speed and language allow you to customize the output without cluttering the request. This approach keeps your integration lightweight and efficient, perfect for indie projects with limited resources.

  • - Standard JSON request body
  • - Minimal required fields: model, input, voice
  • - Optional parameters for speed and language

Rate limits and scalability

Sound wave illustration for: Rate limits and scalability

Our API enforces a rate limit of 60 requests per minute per active key. For new accounts without a top-up, this limit is initially lower at 10 requests per minute. This structure ensures stable performance while keeping costs predictable for indie developers who need reliable audio generation without enterprise bloat.

Requests are processed one after another, so under load a request may wait in a queue. Longer texts split into parts will join the resulting audio files seamlessly. This approach suits small to medium projects where occasional queue delays are acceptable in exchange for transparent, per-character pricing.

60 requests per minute

Each API key allows up to 60 requests per minute. New accounts start with a stricter limit of 10 requests per minute until the first top-up is made. This ensures fair usage while allowing developers to scale as their project grows and their balance increases.

  • 60 requests/minute after top-up
  • 10 requests/minute for new accounts
  • One active key per account

Queued processing under load

Requests are processed one after another, so under heavy load, a request may wait in a queue. Short phrases typically take a few seconds to generate, while longer texts process at roughly real-time speed. This sequential handling keeps infrastructure simple and costs low.

Suitable for small to medium projects

This rate limit and processing model are ideal for indie developers and freelancers who do not need enterprise-grade concurrency. You can split longer texts into parts of up to 4096 characters and join the audio files manually. This workflow is straightforward and avoids the need for complex streaming setups.

Data privacy

Sound wave illustration for: Data privacy

Indie developers often worry about how their text data is handled. Our API is designed with privacy in mind, ensuring that your input text is used solely for the immediate generation of audio and is not added to any training datasets.

Input not used for training

When you send text to the endpoint, it is processed to create your audio file. We do not retain this text for model improvement or resale, keeping your creative content strictly yours.

Audio not stored after response

Once the audio file is generated and returned in the response, it is not stored on our servers. The file exists only in your application’s memory or your local storage, ensuring your final product remains private.

Metadata kept for billing

We do keep minimal metadata—such as the timestamp, character count, and status—to accurately calculate your usage and charges. This data is used exclusively for billing purposes and is not shared with third parties.

Customer support

Sound wave illustration for: Customer support

Our support model is built for developers who prefer clear, asynchronous communication without the noise of live chat widgets. When you need help with integration, billing, or API quirks, you send an email. This ensures your query is documented and can be handled with the necessary technical depth, rather than rushed through a quick chat box.

Email-only support

We process emails directly from our team. There are no automated bots deflecting your questions. You will receive a response from a human who understands the API details, rate limits, and pricing structures. This direct line keeps the communication honest and specific to your actual problem.

No live chat or phone

We do not offer phone numbers or live chat buttons on the site. This keeps our overhead low, which helps us maintain transparent pricing for indie developers. You can drop a message anytime, and it enters a clear queue without the pressure of a real-time call.

Direct access to team

There is no middleman or support tier system. When you email us, your message goes straight to the people who build and maintain the API. This means faster, more accurate answers tailored to the specific constraints of our platform, like our USDT top-up process or voice limitations.

Common use cases

Sound wave illustration for: Common use cases

Indie developers and freelancers often need quick, reliable audio without hiring voice actors. Our API lets you generate natural-sounding speech directly from text, fitting seamlessly into your existing workflows for various content types.

Freelance voiceovers

Use the API to create voiceovers for client projects, such as explainer videos or app tutorials. With eight distinct voices and support for 23 languages, you can match the tone to your client’s brand without managing multiple voice actor schedules.

  • Generate narration for promotional videos in seconds
  • Support multiple languages for global client bases
  • Consistent quality across repeated requests

E-learning content

Create audio lessons for online courses or educational apps. The clear, instructional voices like Sage or Luna work well for tutorials, while the 4096-character limit per request allows for substantial lesson segments without complex splitting logic.

  • Produce consistent audio for course modules
  • Easy integration with LMS platforms via standard API calls
  • Cost-effective scaling for large content libraries

Podcast intro generation

Generate unique intros and outros for podcasts or YouTube channels. You can test different voices like Aria or Felix to find the perfect tone, then batch-generate episodes using the same voice for brand consistency.

  • Customize tone with 8 voice presets
  • Generate multiple episode audios efficiently
  • No monthly fees for ongoing content creation

Limitations to know

Sound wave illustration for: Limitations to know

This API is designed for simplicity, which means you won't find advanced markup or real-time streaming features. Understanding these boundaries helps you build reliable workflows without unexpected surprises.

If your project requires precise audio timing or custom voice generation, you may need to layer additional tools on top of the generated audio files.

No SSML or phoneme control

The API does not support SSML (Speech Synthesis Markup Language) or custom pronunciation lexicons. You cannot control pauses, emphasis, or phoneme-level pronunciation directly in the request.

This keeps the integration simple but means you must rely on natural text formatting or post-process audio for specific timing needs.

  • No SSML tags
  • No custom pronunciation dictionary

No voice cloning

We offer eight curated voices but do not support custom voice cloning for customers. You cannot upload your own voice or design a new one.

This ensures consistent quality and avoids the complexity of training models for each user.

No streaming support

Audio is returned as a complete file, not streamed in real-time. You send a request and receive the full audio file once synthesis is complete.

This is suitable for most indie projects but means you cannot play audio while it is being generated.

Final recommendation

Sound wave illustration for: Final recommendation

Cloud TTS Indie is the pragmatic choice for indie developers and freelancers who need reliable audio generation without enterprise bloat. We offer a straightforward API that integrates easily with your existing workflow, providing transparent pricing and no hidden fees. Our platform is built for those who value simplicity and direct access to tools that just work.

This solution is ideal for indie devs and freelancers looking for a dependable text-to-speech engine. By focusing on core functionality and avoiding unnecessary complexity, we ensure you can generate high-quality audio efficiently, whether for freelance voiceovers, e-learning content, or podcast intros. The open compatibility with OpenAI SDKs makes integration seamless.

Best for indie devs and freelancers

Cloud TTS Indie is the pragmatic choice for indie developers and freelancers who need reliable audio generation without enterprise bloat. We offer a straightforward API that integrates easily with your existing workflow, providing transparent pricing and no hidden fees. Our platform is built for those who value simplicity and direct access to tools that just work.

  • OpenAI-compatible endpoints for easy integration
  • Transparent pricing with no hidden fees
  • No enterprise bloat or complex contracts

Ideal for budget-conscious projects

With a rate of $10 per million characters and no monthly subscriptions, you only pay for what you use. This model is perfect for projects with variable audio needs, ensuring you never overpay for unused capacity. The balance does not expire, allowing you to top up as needed.

Our USDT payment system offers a simple, global-friendly way to manage your budget. Whether you are building a small app or generating content for multiple clients, our pricing scales with your usage, making it easy to keep costs predictable and low.

  • $10 per million characters
  • No monthly subscriptions
  • USDT payment for global flexibility

Start with the free trial

Sign in with Google to receive $0.50 of credit, enough for about 50,000 characters. This trial is valid for 7 days, giving you ample time to test the API, explore the 8 voices, and verify the audio quality. It is a risk-free way to see if Cloud TTS Indie fits your project.

After your trial, you can top up with USDT to continue your work. There are no minimum spend requirements or seats to manage. Just use the API as needed and pay only for the characters you generate.

  • $0.50 free trial credit
  • Valid for 7 days
  • No minimum spend required

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. OpenAI API reference: create speech
  3. W3C WAI: making audio and video accessible
  4. openai-node on GitHub
  5. Creative Commons Attribution 4.0
  6. IETF RFC 7845: Ogg Opus
  7. curl documentation
  8. Node.js documentation
  9. Python documentation
  10. openai-python on GitHub
  11. Tether (USDT)
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site