Cloud TTS API: Quickstart Guide for Developers

By CourseVoice editorial team · Updated 2026-11-19

This guide helps developers integrate the EduEcho text-to-speech API into online course platforms and LMS systems. You will learn how to generate professional voice-overs from lesson scripts programmatically, converting text into audio files for e-learning content.

We cover the complete workflow from obtaining your API key to handling long texts. The instructions use concrete examples with curl and the OpenAI SDK, ensuring you can start generating speech immediately with clear, step-by-step technical details.

Cloud TTS API: Quickstart Guide for Developers

Frequently asked questions

How do I get an API key?

Sign up on /get-api-key/ using Google or email. Accounts are per site. The page displays your key, balance, and usage. A new key issued stops the old one immediately. You can issue a new key anytime. Email and password accounts start without trial credit, while Google sign-ins receive $0.50 credit valid for 7 days.

Can I use the OpenAI SDK?

Yes. The request shape matches the OpenAI speech endpoint. Change the base URL to https://api.api36.info/v1 and use your EduEcho key. The official OpenAI SDKs work directly. No custom SDK is required. You can also use plain HTTP requests. This allows easy integration into existing projects without learning a new library.

What is the base URL?

The base URL is https://api.api36.info/v1. Use this for all API requests. The speech endpoint is POST /v1/audio/speech. Voices and models are available at GET /v1/voices and GET /v1/models. Authentication requires an Authorization header with your Bearer token. Ensure your SDK points to this base URL for correct routing.

Which models are available?

Two models are available: tts-1 and tts-1-hd. Both use the same engine and price. They offer identical audio quality and capabilities. Choose based on preference. The model parameter is required in your request body. Both models support all 8 voices and 23 languages. There is no performance difference between them for standard use cases.

What is the character limit?

Each request supports up to 4096 characters. Spaces and punctuation count toward this limit. For longer texts, split them into parts and join the audio files. Typical speed is roughly real time. Short phrases may take a few seconds. Requests are processed sequentially, so under load, queuing may occur. Plan your splits accordingly.

How do I set the voice?

Specify one of 8 preset voices in the request body. Options include aria, nova, luna, sage, felix, milo, atlas, and orion. Each voice has a distinct tone, from warm narrator to deep documentary. Voices are based on licensed recordings. You can select any voice for any supported language. The voice parameter is required for synthesis.

What formats are supported?

Supported formats are mp3, wav, opus, flac, and pcm. Set the response_format parameter to your preferred type. MP3 is efficient for web delivery. WAV and FLAC offer lossless quality. PCM provides raw audio data. Opus is suitable for low-bandwidth scenarios. All formats are generated instantly upon request completion. Choose based on your integration needs.

What is the rate limit?

The limit is 60 requests per minute per key. Before the first top-up, the limit is 10 requests per minute. Requests are processed sequentially. Under load, requests may wait in a queue. Exceeding the limit may result in delays or errors. Monitor your usage via the dashboard. Top-ups restore higher limits automatically within minutes.

How are failed requests handled?

Failed requests are free. If synthesis fails, the charge is returned in full. No credit is deducted for unsuccessful attempts. You can retry the request without penalty. Check the response status for details. Ensure your input text is valid to avoid failures.

Does the API support streaming?

No streaming is supported. Audio is returned as a complete file in the response. There is no WebSocket or real-time partial audio. You must wait for the full generation to complete. This is suitable for batch processing or on-demand generation. For real-time needs, consider buffering the full response in your application. No SSML or emotion tags are available.

Can I use SSML?

No SSML support is available. The API accepts plain text input. You cannot use SSML tags for pronunciation or pauses. Custom pronunciation lexicons are also not offered. Voices are based on licensed recordings with standard intonation. For precise control, adjust the text or use speed parameters. This simplifies the integration process for developers.

How do I rotate my API key?

Issue a new key from your dashboard. The new key becomes active immediately. The old key stops working at once. This ensures secure access management. You can rotate keys anytime. No downtime occurs during rotation. Update your applications with the new key promptly. Old keys cannot be reused after rotation.

What happens if I exceed the limit?

Requests may be delayed or queued. The limit is 60 requests per minute. Before top-up, it is 10 per minute. Excess requests wait in a queue. Processing is sequential, so delays increase under load. Monitor usage to avoid bottlenecks in your workflow.

Is the API RESTful?

Yes, the API is RESTful. It uses standard HTTP methods like POST and GET. Requests are JSON-based. Responses include standard status codes. The endpoint structure follows REST conventions. Authentication is via Bearer tokens. This allows easy integration with any HTTP client. No custom protocols or proprietary formats are required.

First request

curl

curl https://api.api36.info/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

Python (openai)

from openai import OpenAI

client = OpenAI(base_url="https://api.api36.info/v1", api_key="tts-...")

with client.audio.speech.with_streaming_response.create(
    model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
    response.stream_to_file("hello.mp3")

Node.js (openai)

import OpenAI from "openai";
import fs from "node:fs";

const client = new OpenAI({ baseURL: "https://api.api36.info/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));
voice
ariafemale
novafemale
lunafemale
sagefemale
felixmale
milomale
atlasmale
orionmale
language
arالعربية
zh中文
daDansk
nlNederlands
enEnglish
fiSuomi
frFrançais
deDeutsch
elΕλληνικά
heעברית
hiहिन्दी
itItaliano
ja日本語
ko한국어
msBahasa Melayu
noNorsk
plPolski
ptPortuguês
ruРусский
esEspañol
swKiswahili
svSvenska
trTürkçe

Get Your API Key

Sound wave illustration for: Get Your API Key

EduEcho provides a text-to-speech API designed for startups building online courses and LMS platforms. This quickstart guide covers the essential steps to generate professional voice-overs from text programmatically, simplifying content production for lesson scripts.

Sign Up Process

Sign Up Process

Navigate to the /get-api-key/ page to create your account. You can register using Google or an email and password combination. Accounts are specific to this site, so ensure you are signing up on api36.info.

Key Management

Key Management

After signing in, you receive an API key starting with "tts-". The dashboard displays your key, balance, and usage statistics. This key authenticates your requests to the API endpoint.

  • One active key per account
  • View balance and character usage
  • Key shown on the dashboard

Key Rotation

You can issue a new API key at any time from the dashboard. When a new key is generated, the previous one stops working immediately, ensuring secure access management for your LMS integration.

First Request with Curl

Sound wave illustration for: First Request with Curl

Generate audio files instantly using standard HTTP requests. This guide demonstrates a basic synthesis call to verify your integration works before building full LMS workflows.

Authentication Header

Include your API key in the Authorization header. Use the format Bearer tts-... to authenticate each request to the endpoint.

JSON Body Structure

Send a POST request with a JSON body containing model, input, voice, and response_format. The input field accepts up to 4096 characters of lesson text.

  • model: "tts-1" or "tts-1-hd"
  • voice: e.g., "aria", "nova"
  • response_format: "mp3", "wav", "opus", "flac", or "pcm"

Response Format

Upon success, the endpoint returns the binary audio file directly in the response body. You can save this file or play it in your course player.

Using the OpenAI SDK

Sound wave illustration for: Using the OpenAI SDK

Leverage existing OpenAI SDKs to integrate EduEcho into your LMS or course platform. By adjusting the base URL, you use standard client libraries without writing custom HTTP logic.

This approach simplifies development, allowing you to generate voice-overs for lesson scripts using familiar method calls while maintaining full control over parameters like voice and speed.

Change Base URL

Configure your SDK client to point to the EduEcho API. Set the base URL to https://api.api36.info/v1 instead of the default OpenAI endpoint.

Use Standard SDK

Use the official OpenAI SDK for your preferred language. Authenticate with your API key in the Authorization header. The request shape matches the standard speech endpoint exactly.

  • Install the standard openai package for your language.
  • Initialize the client with your API key and the new base URL.
  • Call the audio.speech.create method as usual.

Compatible Methods

All standard TTS parameters are supported. Pass model, input, voice, response_format, and speed directly to the SDK method. No custom wrapper classes are required.

  • Model: tts-1 or tts-1-hd.
  • Voice: any of the 8 available presets.
  • Format: mp3, wav, opus, flac, or pcm.

Request Parameters

Sound wave illustration for: Request Parameters

Configure the synthesis engine and voice parameters to match your course content. Select the model for audio quality and choose a voice preset that aligns with your lesson’s tone.

Model Selection

Use tts-1 for standard quality or tts-1-hd for higher fidelity. Both models use the same engine and pricing, so choose based on your storage and bandwidth requirements.

Voice Selection

Choose from eight presets, such as aria for clear narration or atlas for neutral news-style delivery. Any voice can speak any of the 23 languages; set the language parameter if the script’s script does not clearly indicate the language.

Voices are based on licensed recordings and include an inaudible synthetic watermark. Select a voice that matches your educational style, such as nova for upbeat introductions or sage for instructional segments.

Speed Control

Adjust the speed parameter between 0.25 and 4.0 to control playback rate. Slower speeds improve clarity for complex technical lessons, while faster speeds suit review sessions or quick summaries.

Note that changing speed does not alter the character count or cost, but it affects the duration of the generated audio file.

Audio Formats Supported

Sound wave illustration for: Audio Formats Supported

The API supports five audio formats to suit different playback and processing needs. You specify your preferred format in the response_format field of the request body. This allows you to optimize file sizes for web delivery or retain high fidelity for archival.

Each generated file includes an inaudible watermark marking it as synthetic speech, which helps identify AI-generated content in course materials.

MP3 Format

MP3 is the standard format for web playback and most learning management systems. It offers a good balance between file size and audio quality, making it ideal for embedding directly into lesson pages or mobile apps.

It is the default choice for most startups building scalable course platforms where bandwidth efficiency matters.

  • Widely supported by all browsers and media players
  • Smaller file sizes reduce data transfer costs
  • Best for general listener playback

WAV Format

WAV provides uncompressed, high-quality audio suitable for professional editing or high-fidelity playback. Use this format if your editors need lossless audio for post-production adjustments.

It results in larger files compared to MP3, so consider storage implications for large course libraries.

  • Uncompressed, lossless audio quality
  • Ideal for editing and post-production
  • Larger file sizes than MP3

Opus and FLAC

Opus offers superior compression at low bitrates, maintaining high quality while minimizing bandwidth usage. FLAC provides lossless compression, reducing file size without sacrificing any audio data.

Choose Opus for efficient streaming and FLAC for archival-quality storage that preserves the original voice characteristics.

  • Opus: High efficiency, small files
  • FLAC: Lossless compression, archival quality
  • Both support high fidelity
Audio Formats Supported

Rate Limits and Queues

Sound wave illustration for: Rate Limits and Queues

Your API key allows 60 requests per minute, which is sufficient for most batch processing workflows. Each request consumes one unit of your limit, so large audio generation jobs may require careful planning to avoid throttling.

60 Requests Per Minute

The standard rate limit is 60 requests per minute per active key. This allows you to generate roughly one audio file per second continuously for short texts. If you exceed this limit, the API returns a 429 Too Many Requests error until the window resets.

Initial Limit

New accounts start with a lower limit of 10 requests per minute. This applies until you make your first top-up. Once you add funds via USDT (TRC-20), your limit increases to the standard 60 requests per minute automatically.

Queue Processing

Requests are processed sequentially. If you send multiple requests rapidly, they are queued and handled one after another. Long texts may take additional time due to the split-and-join process, so plan your integration accordingly to avoid delays.

Error Handling

Sound wave illustration for: Error Handling

The API guarantees that you only pay for successful synthesis. If a request fails due to server issues or invalid parameters, the character charge is returned to your balance immediately, ensuring no cost for wasted effort.

Failed Request Refund

Failed requests are free. If synthesis fails, the charge is returned in full to your account balance automatically.

Common Error Codes

Standard HTTP status codes indicate request status. Use 4xx codes to correct input errors like invalid voice IDs or character limits, and 5xx codes to retry during temporary server load.

  • 400 Bad Request: Invalid parameters or text exceeds 4096 characters
  • 401 Unauthorized: Missing or invalid Bearer token
  • 429 Too Many Requests: Exceeded 60 requests per minute limit

Retry Logic

Implement exponential backoff for 5xx errors. Since requests are processed sequentially, under load a request may wait in a queue, so brief retries often succeed without consuming additional credits if the error was transient.

Long Text Handling

Sound wave illustration for: Long Text Handling

The API accepts input text up to 4096 characters per request. Any script exceeding this limit must be divided into smaller chunks before being sent to the endpoint.

4096 Character Limit

Each POST request supports a maximum of 4096 characters in the input field. This constraint applies to the raw text string, including spaces and punctuation.

Splitting Text

Split your lesson script into segments of 4096 characters or less. Ensure breaks occur at natural boundaries, such as sentence endings, to maintain audio continuity.

Joining Audio Files

Process each segment individually and concatenate the resulting audio files. This approach ensures consistent playback order without exceeding the per-request character limit.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. These voices are best for core curriculum content where clarity and steady pacing are essential for retention.

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. TRON developer hub: TRC-20
  3. Node.js documentation
  4. LibriTTS-R paper (arXiv 2305.18802)
  5. ISO 639 language codes
  6. openai-node on GitHub
  7. Python documentation
  8. OpenAI API reference: create speech
  9. openai-python on GitHub
  10. W3C WAI: making audio and video accessible
  11. curl documentation
  12. MDN: Web Speech API

More on this site