Online Text to Speech Free: A Simple API for Indie Creators

By Voxable editorial team · Updated 2026-11-18

Welcome to Voxable, the text-to-speech API built for indie developers and no-code creators who want natural-sounding audio without the complexity. This page introduces our simple, OpenAI-compatible endpoint that lets you turn text into audio files with just a few lines of code or a standard HTTP request.

Find clear pricing, 8 licensed voices, and support for 23 languages. Sign in with Google to receive a $0.50 free trial (about 50,000 characters) valid for 7 days, so you can test the quality and speed immediately. Note that email sign-ups start without trial credit. Whether you are building an app or creating content, we provide the tools to scale your project transparently.

Online Text to Speech Free: A Simple API for Indie Creators

Frequently asked questions

Is the text-to-speech really free?

You receive a free trial of $0.50 credit, valid for 7 days, when you sign in with Google. This covers about 50,000 characters. If you create an account with an email and password, you start without this trial credit. After the trial, usage is billed at $0.01 per 1,000 characters.

Can I use the audio for commercial projects?

Yes. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), originating from LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech, but there are no restrictions on how you use the final audio files for commercial projects.

Which programming languages are supported?

The API uses standard HTTP requests, so it works with any programming language that can send JSON. You can use the official OpenAI SDKs by changing the base_url to https://api.playk999.com/v1. Alternatively, you can use plain HTTP or any other library that supports POST requests with JSON bodies.

Do I need to sign a contract?

No, there are no monthly plans, seats, or minimum spends. You simply top up your balance and pay for what you use. There is no enterprise contract or SLA required. You can issue a new API key at any time, and the old one stops immediately, giving you full control.

How many characters can I send at once?

You can send up to 4,096 characters per request. If your text is longer, you should split it into parts of up to 4,096 characters and join the resulting audio files. This ensures efficient processing and avoids hitting the single-request character limit while maintaining the continuity of your audio output.

Are the voices robotic or natural?

The voices are natural-sounding presets based on licensed recordings. We offer eight options, including warm narrators, upbeat presenters, and deep documentary styles. While they are synthetic and carry an inaudible watermark, they are designed to sound human and clear, avoiding the typical robotic feel of older text-to-speech systems.

Can I change the speed of the voice?

Yes, you can adjust the speed between 0.25 and 4.0. This allows you to slow down complex explanations or speed up simple instructions. The speed parameter is part of the JSON body sent to the speech endpoint, giving you precise control over the pacing of the generated audio file.

Is my text data stored?

No, your input text is used only to produce the audio and is not used for training. The generated audio is returned in the response and not stored on our servers. We keep request metadata, such as time, characters, and status, strictly for billing purposes and account management.

What happens if the request fails?

If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successful audio generation. You can retry the request or adjust parameters like speed or voice without worrying about losing credits due to temporary processing errors.

Do you support SSML?

No, we do not support SSML. The API accepts plain text input. If you need specific pronunciation or pacing, you can adjust the speed parameter or choose a different voice preset. We do not offer phoneme dictionaries or custom pronunciation lexicons, keeping the integration simple for no-code users.

Can I clone my own voice?

No, we do not offer custom voice cloning. You cannot upload your own voice or design a new voice. You must choose from the eight available presets. Each voice is based on licensed recordings, and all generated files are marked with an inaudible watermark indicating synthetic speech.

Is there a mobile app?

We don’t offer a dedicated mobile app or browser extension. Instead, you interact with Voxable via our API using HTTP requests or the OpenAI SDK. You can manage your account, view usage, and retrieve your API key through our website’s /get-api-key/ page on any device with a browser.

How do I pay with USDT?

Top up via USDT (TRC-20) on the TRON network. The minimum amount is $5, and credits are added automatically within minutes of confirmation. We do not accept cards, PayPal, or invoices. Your balance never expires, allowing you to fund your account whenever needed.

Is there a limit on total characters per month?

No, there is no limit on the total number of characters you can generate per month. You pay only for what you use at $0.01 per 1,000 characters. Your only constraint is the rate limit of 60 requests per minute per key, which ensures fair usage during high demand.

First request

curl

curl https://api.playk999.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

Why Indie Developers Love Us

Sound wave illustration for: Why Indie Developers Love Us

Turn text into natural audio without building a complex audio engine from scratch. Our platform is designed for indie developers and no-code creators who need a simple, reliable way to add speech to their projects. You get a straightforward experience that integrates easily into your existing workflow, whether you are building a mobile app, a web tool, or an interactive story.

No-Code Friendly

You do not need a dedicated audio team or specialized knowledge to use our API. The interface is designed to be intuitive, allowing you to generate speech with minimal configuration. Simply send a text payload, and receive an audio file ready for playback or download.

  • Simple JSON request structure
  • No complex audio infrastructure required
  • Ideal for solo developers and small teams

Open Standard API

We use the same request shape as the OpenAI speech endpoint. This means you can use the official OpenAI SDKs by simply changing the base URL to https://api.playk999.com/v1. If you already know how to call OpenAI's API, you already know how to use ours.

  • Compatible with OpenAI SDKs
  • Standard JSON body format
  • Easy integration with popular frameworks

Transparent Pricing

Pricing scales with your project. You pay $0.01 per 1,000 characters, with no hidden fees or monthly subscriptions. Failed requests are free, so you only pay for successful audio generation. There are no minimum spends or seats to manage.

  • $0.01 per 1,000 characters
  • No monthly plans
  • Failed requests are free

8 Natural Voices for Any Project

Sound wave illustration for: 8 Natural Voices for Any Project

Choosing the right voice is crucial for connecting with your audience. Our eight presets cover a wide emotional range, from warm narration to energetic promos. You can mix and match to find the perfect tone for your specific project without needing complex audio engineering skills.

Each voice is designed to sound natural and clear, ensuring your text-to-speech output feels professional. Whether you are building an app, creating e-learning content, or generating video assets, these voices provide consistent quality across all use cases.

Female Voices: Aria, Nova, Luna, Sage

Aria offers a warm, clear narrator style, ideal for storytelling or guided tours. Nova brings a bright, upbeat energy perfect for modern apps or promotional content. Luna provides a soft, storytelling tone that works well for calming experiences. Sage delivers a calm, instructional voice, great for tutorials or educational modules.

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

Male Voices: Felix, Milo, Atlas, Orion

Felix is energetic and promo-ready, perfect for short ads or dynamic updates. Milo offers a friendly, conversational tone that feels like a natural dialogue. Atlas provides a neutral, news-style delivery for straightforward information. Orion delivers a deep, documentary voice, adding gravity and seriousness to your content.

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

Licensed from Public Domain Audiobooks

All voices are based on licensed recordings from LibriTTS-R, sourced from LibriVox public-domain audiobook readings. This means you can use these voices in your projects without worrying about complex voice licensing agreements. Each generated file also carries an inaudible watermark to mark it as synthetic speech.

8 Natural Voices for Any Project

Support for 23 Languages

Sound wave illustration for: Support for 23 Languages

Our API supports 23 languages, allowing indie developers to reach global audiences without managing complex language packs. Whether you are building an English-first app or a multilingual e-learning platform, we handle the linguistic nuances so you can focus on your product.

Major Languages: English, Spanish, French, German

Start with high-demand markets. Our voices deliver clear, natural-sounding audio in English, Spanish, French, and German, ensuring your content resonates with the largest user bases.

Asian Languages: Chinese, Japanese, Korean

Expand into Asia with dedicated support for Chinese, Japanese, and Korean. Each voice is optimized for accurate pronunciation and natural rhythm in these distinct linguistic environments.

European & Other: Arabic, Hindi, Russian, Turkish

Go further with support for Arabic, Hindi, Russian, Turkish, and 19 other languages including Italian, Portuguese, and Swedish. Every voice can speak any of the 23 supported languages, giving you flexibility without extra integration work.

Start with a Free Trial

Sound wave illustration for: Start with a Free Trial

Start building your audio features immediately with a free trial. You receive $0.50 of credit (about 50,000 characters) the moment you sign in with Google, allowing you to test the API’s quality without any upfront commitment.

$0.50 Free Credit

This credit covers approximately 50,000 characters, giving you enough room to generate several short phrases or a medium-length paragraph. It is perfect for verifying that the voice styles match your project’s tone before you commit to a larger budget.

  • Generous initial allowance for testing
  • Applies to all models and voices

7-Day Validity

The trial credit is valid for 7 days from the moment you sign up. This window is designed to give you ample time to experiment with different voices and formats without pressure, ensuring you can evaluate the product thoroughly.

No Credit Card Required

You can start generating speech without linking a credit card. When you are ready to scale, top-ups are handled via USDT (TRC-20), keeping payments simple and direct. This approach avoids subscription traps and lets you pay exactly for what you use.

  • Sign up with Google
  • Top up with USDT (TRC-20)

Simple Technical Specs

Sound wave illustration for: Simple Technical Specs

Connect your no-code tools or lightweight scripts to our OpenAI-compatible endpoint. Send a POST request to /v1/audio/speech with your text, chosen voice, and desired format. Our API handles the rest, returning a downloadable audio file instantly.

OpenAI Compatible Endpoint

Use the standard OpenAI SDK or plain HTTP. Simply change the base URL to https://api.playk999.com/v1. Support fields include model, input text, voice selection, response format, and optional speed adjustments.

  • Standard JSON request body
  • Supports tts-1 and tts-1-hd models
  • Works with official OpenAI SDKs

Multiple Audio Formats

Choose the best format for your project: mp3, wav, opus, flac, or pcm. Each request generates a single audio file containing your synthesized speech.

  • mp3 for web and mobile
  • WAV for high-quality editing
  • Opus and FLAC for efficiency
  • PCM for raw audio processing

Real-Time Generation

Text is synthesized at roughly 25 characters per second. This means long texts are processed at approximately real-time speed. Short phrases may take a few seconds due to processing overhead.

  • Roughly real-time speed
  • 25 characters per second
  • Queue processing during high load
Simple Technical Specs

How It Works

Sound wave illustration for: How It Works

We generate natural-sounding speech through a straightforward API workflow designed for indie developers and no-code creators. You send text to our endpoint, and we return a synthesized audio file without requiring complex infrastructure or custom SDKs.

Send Text via API

Use the OpenAI-compatible endpoint at https://api.playk999.com/v1/audio/speech. Send a POST request with your API key, selected voice, and text input (up to 4096 characters). The system handles the synthesis engine, so you can focus on your app logic.

  • JSON body with model, input, voice, and optional language
  • Supports tts-1 and tts-1-hd models
  • Works with official OpenAI SDKs by changing base_url

Receive Audio File

Once synthesis completes, you receive the audio file directly in the response. Unlike streaming solutions that send partial audio chunks in real-time, we deliver the complete file upon request completion. Formats include MP3, WAV, OPUS, FLAC, and PCM.

  • Multiple audio formats for flexible integration
  • Standard HTTP response with audio data
  • No complex WebSocket connections needed

Play or Download

Use the returned audio file in your application. Play it directly in web views, download it for offline use, or pipe it into your app’s audio player. The file is ready to use immediately after receipt.

Common Use Cases

Sound wave illustration for: Common Use Cases

Turn static text into engaging audio without hiring voice actors or learning complex tools. Our API integrates directly into your workflow, letting you generate natural-sounding speech with just a few lines of code.

App Notifications

Replace robotic system alerts with clear, human-like voices. Whether it’s a reminder, a status update, or a greeting, audio notifications keep users engaged without requiring them to read long strings of text.

  • Instant generation for real-time user interactions
  • Support for 23 languages to reach global audiences
  • Simple integration via standard HTTP requests

E-Learning Modules

Create accessible course materials quickly. Convert lesson plans, quizzes, or educational articles into audio files that students can listen to on the go. The calm tones of Sage or Luna work well for instructional content.

  • Consistent voice quality across all lessons
  • MP3 and WAV formats for easy playback
  • No need for studio booking or editing software

Video Content

Add voiceovers to your YouTube videos, demos, or social media clips. Generate high-quality speech in minutes and sync it with your visual assets. Ideal for indie creators who need professional audio without the delay of hiring freelancers.

  • Fast turnaround for content schedules
  • Multiple voices for different characters or segments
  • Direct download of audio files for editing

Technical Limits

Sound wave illustration for: Technical Limits

Understand the boundaries before you build. Knowing these limits helps you design robust integrations that handle text length and rate caps gracefully without unexpected errors.

4096 Characters Per Request

Each API call accepts up to 4096 characters, including spaces and punctuation. For longer texts, split your content into chunks and join the resulting audio files in your application logic.

60 Requests Per Minute

Your API key allows 60 requests per minute once funded. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed.

Queue Processing

Requests are processed sequentially. Under heavy load, your synthesis job may wait in a queue before generation begins. Plan your timing accordingly to avoid latency spikes during peak usage.

Technical Limits

Get Started Today

Sound wave illustration for: Get Started Today

To begin, visit /get-api-key/ and sign up using your Google account. This instant method activates your free trial credit of $0.50, valid for 7 days, without requiring a credit card.

Once registered, you will land on your dashboard where your unique API key is displayed. Copy this key securely; it is the only credential needed to authenticate your requests and manage your account.

Sign Up with Google

Head to the registration page and click the Google sign-in button. This creates your account instantly and grants immediate access to your $0.50 free trial credit, which covers approximately 50,000 characters.

Copy Your API Key

After logging in, your dashboard displays your active API key. Copy this string immediately. It starts with 'tts-' and is required in the Authorization header for every API call.

  • Keep your key secure; anyone with it can use your balance.
  • You can generate a new key at any time, invalidating the old one instantly.

Make Your First Request

Use the provided curl example or your preferred HTTP client. Send a POST request to the API base URL with your key, a model like 'tts-1', and your text input. You will receive the audio file directly in the response.

  • Base URL: https://api.playk999.com/v1
  • Include 'Authorization: Bearer tts-...' in headers.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Indie developers use no-code tools to bring their unique creative game visions to life effortlessly.

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

More on this site