Cloud Text-to-Speech API for Indie Developers

By WordCaster editorial team · Updated 2026-11-18

WordCaster is a cloud text-to-speech API built for indie developers and no-code builders who need to convert text into audio without complex infrastructure. By using standard OpenAI-compatible endpoints, you can integrate high-quality synthetic speech into your applications with minimal code changes. Simply send a JSON request and receive an audio file in seconds.

This page outlines how to get started with our pay-as-you-go model, transparent pricing, and 8 distinct voice presets. You will find concrete examples for integration, details on supported languages, and clear explanations of rate limits and data privacy. Whether you are building app notifications or e-learning content, we provide the reliable API foundation your project needs.

Cloud Text-to-Speech API for Indie Developers

Frequently asked questions

What is a TTS API?

A cloud text-to-speech API lets you send text and receive an audio file via a simple POST request. It uses standard JSON bodies compatible with OpenAI SDKs, making integration easy for indie developers. You specify the model, voice, and format, and the service returns the synthesized audio without requiring complex infrastructure or custom hardware.

How do I get started with the API?

Sign up on /get-api-key/ using Google or email to receive your API key. Use this key with the official OpenAI SDKs by setting the base URL to https://api.playtoto155.com/v1. Send a POST request to /v1/audio/speech with your text and voice selection to generate audio files immediately.

Which voices are available?

There are eight presets based on licensed recordings: female voices aria, nova, luna, and sage; male voices felix, milo, atlas, and orion. Each voice has a distinct tone, from warm narration to deep documentary styles. You can view all available voices and their details by calling the GET /v1/voices endpoint.

What languages does the API support?

The API supports 23 languages including English, Spanish, German, French, Japanese, and Chinese. Any voice can speak any supported language. If the language parameter is omitted, the system guesses the language from the script, defaulting to English for Latin text. Vietnamese, Thai, Indonesian, Ukrainian, Romanian, Czech, Bengali and others are not supported.

How is pricing calculated?

Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free with a full refund. There are no monthly plans, seats, or minimum spends, allowing you to pay only for the audio you actually generate.

Is there a free trial?

Yes, signing in with Google provides $0.50 of credit, valid for 7 days. This allows approximately 50,000 characters of generation. Accounts created with email and password start without trial credit. The balance does not expire, and you can top up later using USDT on the TRON network.

What audio formats can I receive?

You can receive audio in mp3, wav, opus, flac, or pcm formats. Specify your preferred format in the response_format field of your request. The API returns the audio file directly in the response, ensuring you get the exact file type needed for your specific application or workflow.

Are there rate limits?

The limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so under load, you may experience queue delays. Longer texts are split into parts of 4096 characters and joined after generation.

How long are my request logs kept?

Request metadata, including time, characters, and status, is kept for billing purposes. Input text is used only to produce audio and is not stored or used for training. Generated audio is returned in the response and is not stored on our servers after delivery.

Can I use the audio commercially?

The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. The generated files carry an inaudible watermark marking them as synthetic speech. You can use these files in your projects, but the voices are not custom clones of specific individuals.

Does the API support streaming?

No, the API does not support streaming, WebSockets, or real-time partial audio. It returns the complete audio file after synthesis is finished. For long texts, the system splits the input into parts of up to 4096 characters, generates each part, and joins them, but this is not real-time streaming.

Is SSML supported?

No, the API does not support SSML (Speech Synthesis Markup Language). You cannot use phoneme dictionaries or custom pronunciation lexicons. You control the output primarily through the voice selection, speed parameter, and the text input itself, keeping the integration simple for no-code builders.

Can I clone my own voice?

No, custom voice cloning is not offered. You cannot upload your own voice or design a new one. The eight available presets are based on licensed recordings. If you need a specific voice, you must choose from the existing options like aria, nova, or atlas.

How do I top up my balance?

Top up using USDT on the TRON network (TRC-20). The minimum amount is $5, and credits are added automatically within minutes of transfer. There are no credit cards, PayPal, or subscriptions. You can issue a new API key at any time if needed.

First request

curl

curl https://api.playtoto155.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

How it works

Sound wave illustration for: How it works

The API processes your text input and returns an audio file in a single request. You send a JSON payload containing the text, voice selection, and format preferences, then receive the synthesized speech without managing complex infrastructure or background jobs.

Integration is straightforward because the endpoint mirrors the OpenAI speech API structure. By updating your base URL, you can use the official OpenAI SDKs or any standard HTTP client to send requests and handle responses immediately.

Send text, receive audio

Send text, receive audio

Input plain text into the API and receive a generated audio file. The system handles the synthesis process, returning the audio data directly in the response. This simple workflow allows you to integrate audio generation into any application without building custom voice engines.

Requests are processed sequentially, ensuring consistent output. For longer texts, you can split the input into chunks of up to 4096 characters, generate each part, and join the resulting audio files seamlessly.

  • Supports up to 4096 characters per request
  • Returns audio in specified formats
  • Processes requests sequentially for consistency

OpenAI-compatible endpoints

The API uses 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.playtoto155.com/v1 and providing your API key. No learning curve for developers already familiar with OpenAI’s integration pattern.

This compatibility extends to other SDKs that rely on standard REST principles. You can integrate the TTS service into existing workflows with minimal code changes, leveraging familiar authentication and request structures.

  • Same request shape as OpenAI speech endpoint
  • Use official OpenAI SDKs with updated base_url
  • Compatible with standard REST clients

Simple JSON requests

Send a POST request to /v1/audio/speech with a JSON body containing model, input, voice, and response_format. The API handles the rest, synthesizing the text and returning the audio file. This simplicity reduces integration time and minimizes errors in your application code.

You can also specify optional parameters like speed (0.25–4.0) and language (ISO code) to customize the output. The system automatically detects the language if not provided, defaulting to English for Latin-script text.

  • POST to /v1/audio/speech
  • JSON body with model, input, voice
  • Optional speed and language parameters

Voices and languages

Sound wave illustration for: Voices and languages

WordCaster provides eight distinct voice presets, ranging from warm narrators to deep documentary tones. Each voice is based on licensed recordings from LibriTTS-R and LibriVox, ensuring clear, professional audio for your projects without the need for complex infrastructure.

8 distinct voice presets

Choose from four female voices: Aria (warm, clear narrator), Nova (bright, upbeat), Luna (soft, storytelling), and Sage (calm, instructional). Male options include Felix (energetic), Milo (friendly), Atlas (neutral news), and Orion (deep documentary). All voices are synthetic and carry an inaudible watermark.

23 supported languages

The API supports 23 languages, including English, Spanish, German, French, Japanese, and Arabic. Any voice can speak any supported language, allowing you to maintain consistent character tones across diverse linguistic content without needing multiple voice models.

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

Automatic language detection

Set the optional language field to an ISO code for precision. If omitted, the system guesses the language from the script, defaulting to English for Latin text. Explicitly set language for non-English Latin-script text to ensure accurate synthesis.

Integration

Sound wave illustration for: Integration

Integration is straightforward: send a JSON payload to our endpoint and receive an audio file. The API mirrors the OpenAI speech endpoint structure, meaning you only need to adjust your base URL to https://api.playtoto155.com/v1. This compatibility allows you to use standard HTTP clients or existing SDKs without rewriting your integration logic.

cURL examples

You can start instantly with a simple cURL command. This approach requires no library installation, making it ideal for quick prototypes or no-code automation tools that support HTTP requests.

  • Send text via POST request
  • Specify model, voice, and format
  • Receive audio file in response

OpenAI SDK support

Since the request shape matches the OpenAI speech endpoint, you can use the official OpenAI SDKs by simply pointing them to our API base. This reduces setup time for developers already familiar with the OpenAI ecosystem.

No custom SDK needed

We do not provide a proprietary SDK. By adhering to a widely recognized standard, we ensure long-term compatibility and flexibility. You retain full control over your integration stack without being locked into a specific vendor library.

Pricing model

Sound wave illustration for: Pricing model

WordCaster uses a straightforward pay-as-you-go model based on character count. You are charged $10 per million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you only pay for successful synthesis.

Pay per character

The cost is transparent and predictable. At roughly $0.01 per 1,000 characters, long texts scale linearly. For example, a 10,000-character document costs $0.10. This simplicity helps indie developers budget accurately without worrying about complex tier structures.

  • Rate: $10 per 1,000,000 characters
  • Spaces and punctuation count as characters
  • Failed requests incur no charge

Free trial credit

New accounts signing in with Google receive $0.50 in trial credit, valid for 7 days. This provides approximately 50,000 characters of usage. Email-based accounts start with zero balance and require an immediate top-up to begin.

No monthly subscriptions

There are no monthly plans, seats, or minimum spend requirements. You can top up with USDT (TRC-20) on the TRON network. The minimum top-up is $5, and your balance never expires, allowing you to pause and resume projects freely.

  • No monthly fees or subscriptions
  • No minimum spend required
  • Balance does not expire

Technical details

Sound wave illustration for: Technical details

Requests are processed sequentially, meaning longer texts may experience queueing during high load. Each request is limited to 4,096 characters; larger texts must be split and joined by the client. Standard generation speed is roughly real-time.

Rate limits and queues

Keys are limited to 60 requests per minute (10 per minute before the first top-up). Requests are processed one after another, so under load, synthesis may wait in a queue. Failed requests do not consume your limit.

Audio formats available

Output is returned as an audio file in one of five formats: mp3, wav, opus, flac, or pcm. Speed can be adjusted between 0.25 and 4.0. Every generated file includes an inaudible watermark marking it as synthetic speech.

Data privacy policy

Input text is used solely to produce the audio and is not used for training models. Generated audio is returned in the response and not stored on our servers. Request metadata (time, characters, status) is retained only for billing purposes.

Technical details

Use cases

Sound wave illustration for: Use cases

Turn static text into engaging audio without building a complex pipeline. This API lets indie developers and no-code builders integrate voice features directly into their projects with simple JSON requests.

App notifications

Replace generic tones with clear, natural voice messages. Users receive updates in their preferred language, enhancing accessibility and engagement without requiring external media files.

  • Instant text-to-speech for push notifications
  • Support for 23 languages
  • Simple integration via REST API

E-learning content

Convert course materials, quizzes, or instructional text into audio. Students can listen to lessons on the go, using voices like Sage for calm instruction or Nova for upbeat energy.

  • 8 distinct voice presets
  • Speed adjustment from 0.25x to 4.0x
  • No custom voice cloning needed

Blog audio summaries

Offer readers an audio version of your articles automatically. Send the post text to the API and receive an MP3 or WAV file to embed directly on your site.

  • Multiple audio formats available
  • Pay only for characters used
  • No monthly subscription required

Why choose this API

Sound wave illustration for: Why choose this API

WordCaster removes the guesswork from TTS integration. We offer a straightforward pay-as-you-go model where you only pay for what you use, with no monthly subscriptions or minimum spend requirements. Your balance never expires, allowing you to pause projects without losing credit.

Transparent billing

Every request is charged at $0.01 per 1,000 characters. Failed requests are free, ensuring you only pay for successful synthesis. You can track exact usage and remaining characters directly in your dashboard.

  • Pay per 1,000 characters
  • Failed requests are free
  • Balance does not expire

No hidden fees

There are no per-seat charges or enterprise contracts. The price remains constant regardless of volume. Top-ups via USDT (TRC-20) are credited automatically, with no surprise VAT invoices or processing delays.

Developer-first design

Our API mirrors the OpenAI speech endpoint structure, allowing you to use existing OpenAI SDKs by simply changing the base URL. This compatibility means less code rewriting and faster integration for indie developers and no-code builders.

Getting started

Sound wave illustration for: Getting started

Getting started with WordCaster takes less than two minutes. Create an account on the /get-api-key/ page using Google or email, then generate your unique API key. The dashboard immediately displays your balance, usage stats, and a ready-to-use cURL example.

Create your account

Visit the signup page and choose Google or email authentication. If you sign in with Google, you receive a $0.50 trial credit valid for 7 days, enough for approximately 50,000 characters. Email-based accounts start without trial credit but allow immediate top-ups via USDT (TRC-20).

Generate your API key

Once registered, your dashboard provides a single active API key prefixed with tts-. You can issue a new key at any time; the old one stops instantly. Use this key in the Authorization: Bearer header for all requests.

Make your first request

Send a POST request to https://api.playtoto155.com/v1/audio/speech with your JSON payload. Specify the model (tts-1 or tts-1-hd), input text, voice preset, and desired format. The API returns the audio file directly in the response.

Support and limits

Sound wave illustration for: Support and limits

This API is designed for developers who prefer to focus on building rather than waiting on hold. Support is handled entirely via email, ensuring that every query receives a detailed, written response without the pressure of real-time availability. You can reach the team at any time, and they will get back to you as soon as possible.

There is no live chat widget to interrupt your workflow or generic phone numbers to navigate. This approach keeps operational costs low, which directly supports our transparent, pay-as-you-go pricing model. If you need assistance with integration or billing, a simple email is the most efficient channel.

Email support only

All support requests are managed through email. This ensures that complex technical questions receive thorough, documented answers that you can reference later. There is no need to repeat your issue to a different agent or wait on hold.

  • Direct email contact for all inquiries
  • Detailed written responses for technical clarity
  • No ticket queue delays

No live chat

You will not find a live chat bubble on this site. We believe that asynchronous communication is more respectful of your development time. It allows you to provide full context for your question and receive a complete answer without breaking your focus.

Standard uptime

We do not offer an official Service Level Agreement (SLA) or uptime guarantee. The API is reliable for typical development and production workloads, but we do not provide enterprise-grade contracts for critical infrastructure dependencies. If the service is down, it is usually resolved quickly.

  • No SLA or uptime guarantee
  • No enterprise contracts
  • Reliable for standard workloads

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Each voice is based on licensed recordings from LibriVox, ensuring clear, professional audio without licensing complexity.

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. FFmpeg documentation
  3. LibriTTS-R corpus (OpenSLR 141)
  4. Creative Commons Attribution 4.0
  5. TRON developer hub: TRC-20
  6. LibriTTS-R paper (arXiv 2305.18802)
  7. MDN: Web Speech API
  8. IETF RFC 7845: Ogg Opus
  9. W3C WAI: making audio and video accessible
  10. Python documentation
  11. openai-node on GitHub
  12. LibriVox public-domain audiobooks

More on this site