Cloud TTS API: 8 Voices, 23 Languages for Apps

By EchoLoom editorial team · Updated 2026-11-18

This page explains how to integrate EchoLoom’s cloud Text-to-Speech API into your mobile application. We provide a simple JSON endpoint compatible with standard HTTP clients, allowing your team to generate high-quality speech audio files without managing complex infrastructure. The service handles voice synthesis, formatting, and billing so you can focus on user experience.

Designed for startups, our API supports 8 distinct voices and 23 languages, ensuring consistent quality across global user bases. You receive clear, synthetic audio files via standard API responses, ready for playback in your app. This page details the technical requirements, pricing structure, and integration steps to help you deploy speech features efficiently.

Cloud TTS API: 8 Voices, 23 Languages for Apps

Frequently asked questions

Is the text to speech API really free?

No, the API is not free. You receive a free trial of $0.50 credit (valid for 7 days) when signing in with Google. After the trial expires or is exhausted, you must top up your balance using USDT on the TRON network to continue generating audio. There are no monthly plans or minimum spend requirements.

How many characters are in the free trial?

The free trial provides $0.50 of credit, which equals approximately 50,000 characters. This trial is available only when you sign in with Google. Accounts created with email and password start without this trial credit. Once the credit is used, you must top up your account to continue using the service.

Which voices are available for mobile apps?

You have access to 8 voice presets: Aria, Nova, Luna, and Sage (female); Felix, Milo, Atlas, and Orion (male). Each voice has a distinct tone, such as warm, bright, or neutral. All voices can speak any of the 23 supported languages, allowing you to select the best fit for your app’s user experience.

What languages does the API support?

The API supports 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. If the language is not specified, it is guessed from the script.

Does the API support streaming audio?

No, the API does not support streaming, WebSocket, or real-time partial audio. You send a POST request with text and receive the complete audio file in the response. You must handle the full file delivery to your users. This simplifies integration but means you cannot play audio while it is generating.

Can I use the generated audio in my app?

Yes, you can use the generated audio in your app. Each generated file carries an inaudible watermark marking it as synthetic speech. Input text is used only to produce the audio and is not used for training. The audio is returned in the response and not stored by the API.

How do I pay with USDT?

You pay using USDT on the TRON network (TRC-20) only. The minimum top-up amount is $5. After you send the transfer, the credit is credited to your account automatically within minutes. There are no cards, PayPal, subscriptions, or invoices. Your balance does not expire, and you can issue a new API key anytime.

Is there a minimum spend requirement?

No, there is no minimum spend requirement. You can top up any amount above the $5 minimum for USDT transfers. There are no monthly plans, no seats, and no minimum spend. You only pay for the characters you generate, at a rate of $0.01 per 1,000 characters.

What happens if the synthesis fails?

If synthesis fails, the charge is returned in full. Failed requests are free, so you do not lose any credit. The API processes requests one after another, so under load a request may wait in a queue.

Do I need to handle audio file storage?

No, you do not need to handle audio file storage by the API. The generated audio is returned directly in the API response. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. You only need to store the audio file you receive if you want to cache it.

Can I change the voice after generation?

No, you cannot change the voice after generation. The voice is selected in the request body and baked into the audio file. You can generate a new audio file with a different voice by sending another POST request. Each generation is a separate request with its own cost and processing time.

Does the API support SSML?

No, the API does not support SSML. It accepts plain text input up to 4096 characters. You cannot use SSML tags for pronunciation or pauses. If you need specific control, you must manage it in your text input or post-process the audio. The API focuses on simplicity for mobile app integration without complex markup.

Is there a limit to the text length?

Yes, each request accepts up to 4096 characters. If your text is longer, you must split it into parts of up to 4096 characters and join the resulting audio files. Spaces and punctuation count as characters. This limit ensures consistent processing times and allows for efficient queue management under load.

How long does it take to generate audio?

Typical speed is roughly real time, about 25 characters of text per second of generation. Short phrases take a few seconds. Requests are processed one after another, so under load a request may wait in a queue. Longer texts will take longer to process proportionally to their duration.

First request

curl

curl https://api.playtt39.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

Generate Speech for Your App

Sound wave illustration for: Generate Speech for Your App

EchoLoom provides a straightforward text-to-speech API designed for mobile app developers who need reliable audio generation without managing infrastructure. Send a JSON payload with your text, and receive a high-quality audio file in seconds. This approach keeps your team focused on user experience while we handle voice synthesis, formatting, and billing.

Simple JSON API

Simple JSON API

Interact with our API using standard HTTP requests. The endpoint POST https://api.playtt39.com/v1/audio/speech accepts JSON bodies similar to the OpenAI speech endpoint, allowing you to use familiar OpenAI SDKs by simply changing the base_url. Specify your model, input text, voice, and response_format in a single call.

  • Standard JSON request body
  • Compatible with OpenAI SDKs
  • Single endpoint for synthesis

High Quality Audio

Generate natural-sounding speech using one of eight distinct voices, including options like Aria for warm narration or Felix for energetic promos. Each voice is based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. The API handles formatting and audio encoding, returning files in formats like mp3, wav, opus, or flac.

Easy Integration

Integrate speech synthesis directly into your mobile app with minimal code. Texts up to 4096 characters are processed efficiently, with longer texts automatically split and joined. You control the speed (0.25–4.0) and format, ensuring the audio fits your app’s performance and storage constraints without extra processing steps.

  • Supports mp3, wav, opus, flac, pcm
  • Speed control from 0.25 to 4.0
  • AUTOMATIC splitting for long texts

Voices and Languages

Sound wave illustration for: Voices and Languages

EchoLoom offers eight distinct voice presets designed for mobile app contexts, ranging from warm narrators to energetic promo styles. Each voice is engineered for clarity and natural flow, ensuring your app’s audio feels professional without requiring complex tuning.

8 Distinct Voices

Choose from four female voices (Aria, Nova, Luna, Sage) and four male voices (Felix, Milo, Atlas, Orion). These presets cover common use cases like storytelling, news, and conversational interfaces.

23 Supported Languages

Support includes Arabic, Chinese, English, French, German, Japanese, Korean, Spanish, and more. Any voice can speak any supported language. Set the language field explicitly for non-English Latin text to avoid default English guessing.

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

Consistent Quality

All voices use the same underlying engine, ensuring uniform audio quality across your entire application. Generated files include an inaudible watermark that marks them as synthetic speech.

Pricing for Startups

Sound wave illustration for: Pricing for Startups

Our pricing model is straightforward: you pay only for what you use. At $10 per million characters, or $0.01 per 1,000 characters, costs scale linearly with your app’s usage. Spaces and punctuation count toward the total, ensuring predictable billing without hidden fees for short phrases or long texts.

There are no monthly subscriptions, no seats to manage, and no minimum spend. If a synthesis request fails, you are not charged, so you only pay for successful audio generations. This structure allows startups to test integrations without upfront commitments or managing complex tiered plans.

Pay Per Character

Charge $0.01 per 1,000 characters. Failed requests are free.

Balance does not expire. Top-ups are credited automatically within minutes after the transfer.

  • $10 per 1,000,000 characters
  • $0.01 per 1,000 characters
  • Failed requests are free

No Monthly Fees

No monthly plans, seats, or minimum spend. You can use the API at any volume without recurring costs. This flexibility is ideal for apps with fluctuating traffic or those in the early stages of user acquisition.

You maintain full control over your budget. Since there are no subscriptions, you can pause usage without losing access to previous integrations or data.

Crypto Payments

Top up your balance using USDT on the TRON network (TRC-20). The minimum deposit is $5, and credits are added automatically within minutes of transfer. We do not accept credit cards, PayPal, or invoices, keeping the process simple and borderless.

No VAT or regional tax variations apply. Your balance remains available until used, providing a stable financial foundation for your API integration without the friction of traditional payment gateways.

Technical Details

Sound wave illustration for: Technical Details

EchoLoom’s API accepts text and returns audio files in MP3, WAV, OPUS, FLAC, or PCM formats, allowing seamless integration into mobile app audio players. Each request supports up to 4,096 characters; longer texts must be split into parts by the client and the audio files joined.

Format Support

Output formats are selected via the response_format field. MP3 is recommended for general use due to its small file size and universal playback support, while WAV and FLAC offer lossless quality for higher-fidelity requirements.

  • MP3, WAV, OPUS, FLAC, PCM

Rate Limits

The API allows 60 requests per minute per key after initial top-up. New accounts start with a limit of 10 requests per minute. Requests are processed sequentially, so high volume may introduce slight queueing delays.

  • 60 requests/minute (post top-up)
  • 10 requests/minute (initial)

Speed Control

The speed parameter accepts values between 0.25 and 4.0, allowing you to adjust the playback rate to fit your app’s user experience. The default speed is 1.0. Text processing typically takes about 25 characters per second of audio generated.

  • Speed range: 0.25–4.0

How It Works

Sound wave illustration for: How It Works

Integration begins with a standard HTTP POST request to the speech endpoint. Your backend sends a JSON payload containing the text input, selected voice, and desired audio format. The API processes the request, generating high-fidelity speech without requiring complex infrastructure management on your part.

Send Text

Structure your request body with the input field containing up to 4096 characters of text. Specify the model (tts-1 or tts-1-hd), the voice preset, and the response_format (mp3, wav, opus, flac, or pcm). You can also adjust the speed between 0.25 and 4.0 or define a specific language ISO code if the script does not clearly indicate the language.

  • Include your API key in the Authorization: Bearer header.
  • Keep input text under 4096 characters per request.
  • Choose from 8 distinct voice presets.

Receive Audio

Upon successful synthesis, the API returns the audio file directly in the response body. Failed requests incur no charge, ensuring you only pay for completed generations. For texts exceeding the character limit, split the input into parts, generate each segment, and concatenate the resulting audio files on your end.

  • Response contains the raw audio data.
  • Failed requests are free.
  • Audio is returned after a few seconds for short phrases; longer texts take time proportional to length.

Play in App

Once received, the audio file can be stored temporarily or played directly within your mobile application. Since the API handles formatting and generation, your team focuses on delivering a seamless user experience. The synthetic watermark in the audio ensures traceability without affecting playback quality.

How It Works

Why EchoLoom?

Sound wave illustration for: Why EchoLoom?

EchoLoom is a standalone API provider, not affiliated with major tech giants. You integrate directly with our endpoint without depending on third-party brand ecosystems, ensuring your voice infrastructure remains independent and portable.

Billing is strictly usage-based with no hidden tiers or minimum commitments. You pay only for characters generated, and failed requests are refunded automatically. Transactions are handled via USDT on TRON, eliminating currency conversion fees and invoice delays.

No Vendor Lock-in

Our API follows the same JSON structure as major industry standards, allowing easy migration or multi-provider strategies. Since we do not use proprietary formats, your generated audio files and code remain fully under your control.

Transparent Billing

Costs are calculated per 1,000 characters at a flat rate. Your dashboard displays real-time usage and balance, so you can predict expenses accurately before deployment. There are no surprise charges for high-volume bursts.

Developer First

We provide standard HTTP endpoints and cURL examples that work with any language. You can issue a new API key instantly if the old one is compromised, with the old key stopping immediately.

  • Standard JSON request/response format
  • Instant key rotation capability
  • No proprietary SDK required

Getting Started

Sound wave illustration for: Getting Started

Start building with $0.50 in trial credit when you sign in with Google. This covers approximately 50,000 characters and is valid for 7 days, allowing you to test integration without immediate payment.

Create an account on the /get-api-key/ page to retrieve your unique API key. Use this key in your Authorization header to begin sending requests to the API base.

Free Trial Credit

Sign up with Google to receive $0.50 in credit immediately. This amount supports about 50,000 characters of text synthesis, valid for 7 days. Email-based accounts start with zero balance.

API Key Setup

Navigate to /get-api-key/ to generate your active key. Include it in your requests as Authorization: Bearer <key>. You can issue a new key at any time, which instantly invalidates the previous one.

  • Key format: tts-...
  • One active key per account
  • Instant invalidation on new key generation

Quick Demo

Send a POST request to https://api.playtt39.com/v1/audio/speech with your text and voice selection. The API returns an audio file in your chosen format, ready for playback in your mobile app.

Test with short phrases first. Note that generation takes a few seconds, and requests are processed sequentially under load.

  • Endpoint: POST /v1/audio/speech
  • Format: JSON
  • Response: Audio file

Use Cases

Sound wave illustration for: Use Cases

Leverage EchoLoom’s TTS API to convert large text libraries into audio files for mobile audiobook apps. With support for 23 languages and multiple voice presets, developers can offer diverse narrators without managing infrastructure.

Generate dynamic audio for push notifications or in-app alerts. The API’s consistent speed and clear speech ensure users receive critical updates without distraction, enhancing engagement through reliable audio delivery.

Audiobooks

Convert chapter texts into MP3 or WAV files using the API. Split long texts into 4096-character chunks and join the audio seamlessly for a smooth listening experience.

  • Support for 23 languages including English, Spanish, and Japanese
  • Voice presets like Luna for storytelling or Atlas for news

Notifications

Inject voice into push notifications for a more personal touch. Use the speed control (0.25–4.0) to adjust delivery pace based on context, such as urgent alerts vs. daily updates.

  • Real-time generation via POST endpoint
  • Low latency suitable for immediate playback

Accessibility

Provide audio alternatives for text content. Ensure compliance with accessibility standards by offering clear, synthetic speech that reads UI text or article content for visually impaired users.

  • Multiple output formats (MP3, WAV, OPUS, FLAC, PCM)
  • Consistent voice quality across all languages

Support

Sound wave illustration for: Support

Support is by email only. There is no phone number or live chat; you can reach our team at any time, and we aim to respond within one business day.

Our documentation covers the full API reference, including request formats, error codes, and SDK examples. It is designed to help you integrate the speech synthesis engine into your mobile app quickly and without guesswork.

Email Support

For specific issues regarding your account or API key, send an email to [email protected]. Please include a description of the problem for faster resolution.

  • Direct email access
  • No live chat waiting rooms

Documentation

The docs provide clear examples for sending text and receiving audio files. You can find code snippets for cURL to get started immediately.

  • API reference
  • Code examples
  • Error handling guide

Community

While we do not host a dedicated forum, developers often share integration tips on GitHub and Stack Overflow. You can search these platforms for solutions related to the OpenAI-compatible endpoint structure.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. OPUS offers efficient compression for mobile data, while WAV provides uncompressed quality for high-fidelity needs.

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. curl documentation
  4. MDN: Web Speech API
  5. IETF RFC 7845: Ogg Opus
  6. W3C WAI: making audio and video accessible
  7. TRON developer hub: TRC-20
  8. Tether (USDT)
  9. openai-node on GitHub
  10. Python documentation
  11. Node.js documentation
  12. ISO 639 language codes

More on this site