Frequently asked questions
What is the base URL for the API?
The API base URL is https://api.playn57.com/v1. You send POST requests to https://api.playn57.com/v1/audio/speech for synthesis. Other endpoints include GET /v1/voices and GET /v1/models. This structure mirrors the OpenAI API, allowing you to use existing OpenAI SDKs by simply updating the base_url configuration in your client settings.
Can I use the OpenAI Python SDK with this API?
Yes. The endpoint shape matches the OpenAI speech endpoint exactly. You can use the official OpenAI Python SDK by changing the base_url to https://api.playn57.com/v1 and providing your EchoPress API key. This allows you to leverage familiar code structures without needing a custom library for basic integration.
How do I set the speed of the voice?
Include a speed field in your JSON request body. The value must be a number between 0.25 and 4.0. This adjusts the playback speed of the generated audio relative to normal speech. The default speed is 1.0. This parameter works with all eight voice presets and any supported language.
What is the maximum length of text per request?
Each request supports up to 4096 characters of input text. Spaces and punctuation count toward this limit. If your article exceeds this length, you must split the text into smaller chunks. Generate audio for each chunk separately and then join the resulting audio files to create a complete recording.
Does the API support streaming audio?
No. The API does not support streaming, WebSocket connections, or real-time partial audio delivery. You send a request and receive the complete audio file in the response. This synchronous approach simplifies integration for publishers who need to store or embed full audio files rather than handling live streams.
How do I rotate my API key?
You can issue a new API key at any time from your account dashboard. When you generate a new key, the old one stops working immediately. This ensures that only your current active key is valid. You can manage this directly on the /get-api-key/ page without waiting for a cooldown period.
What happens if I exceed the rate limit?
The limit is 60 requests per minute per key. If you exceed this, subsequent requests may queue or fail. New accounts start with a lower limit of 10 requests per minute until you make your first top-up. Exceeding the limit does not incur extra charges, but it delays processing.
Is SSML supported in the input text?
No. The API does not support SSML (Speech Synthesis Markup Language). You cannot use SSML tags to control pauses, pronunciation, or emphasis. Input is plain text only. If you need precise control over delivery, you must manage pacing by splitting your text into separate requests with appropriate timing logic.
How do I specify the language for Latin script text?
If your text uses Latin script but is not English, you must explicitly set the language field to the ISO code. Otherwise, the API defaults to English. Supported languages include French, German, Spanish, and others. Setting this field ensures correct pronunciation and intonation for non-English Latin-script content.
Can I generate audio in multiple formats?
Yes. You can specify the response_format field in your request. Supported formats include mp3, wav, opus, flac, and pcm. Choose the format that best fits your blog’s audio player or storage requirements. MP3 is recommended for general web use due to its balance of quality and file size.
What is the difference between tts-1 and tts-1-hd?
Both models use the same underlying engine and incur the same price of $10 per million characters. Both models use the same engine and price; tts-1-hd is the high-quality variant. Choose tts-1-hd for better fidelity, or tts-1 for standard quality. The choice does not affect processing speed or character limits.
How do I handle long articles with the 4096 char limit?
Split your article into parts of up to 4096 characters each. Send each part as a separate request to the API. Receive the audio file for each chunk, then join them sequentially to create a single continuous audio file. This ensures you stay within the per-request character limit.
Is the API key case-sensitive?
Yes. Your API key is a specific string starting with tts-. Ensure you copy it exactly from the /get-api-key/ page, preserving uppercase and lowercase letters. The key is sent in the Authorization: Bearer header. Using an incorrect case or extra spaces may result in authentication errors.
Do I need to install any specific libraries?
No specific library is required. You can use plain HTTP requests or the official OpenAI SDK. If using the OpenAI SDK, just update the base_url to https://api.playn57.com/v1. Any HTTP client that can send JSON payloads and handle the Bearer token authentication will work correctly with the API.
First request
curl
curl https://api.playn57.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.mp3Python (openai)
from openai import OpenAI
client = OpenAI(base_url="https://api.playn57.com/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.playn57.com/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 | |
|---|---|
aria | female |
nova | female |
luna | female |
sage | female |
felix | male |
milo | male |
atlas | male |
orion | male |
| language | |
|---|---|
ar | العربية |
zh | 中文 |
da | Dansk |
nl | Nederlands |
en | English |
fi | Suomi |
fr | Français |
de | Deutsch |
el | Ελληνικά |
he | עברית |
hi | हिन्दी |
it | Italiano |
ja | 日本語 |
ko | 한국어 |
ms | Bahasa Melayu |
no | Norsk |
pl | Polski |
pt | Português |
ru | Русский |
es | Español |
sw | Kiswahili |
sv | Svenska |
tr | Türkçe |
Quickstart Guide
Turn your WordPress articles into engaging audio in minutes. EchoPress integrates naturally into your publishing workflow, allowing readers to listen to your content without leaving the page.
Follow this simple guide to generate your first audio file using standard tools you already know.
Get Your API Key
Visit /get-api-key/ to create an account via Google or email. Your unique API key appears immediately on the dashboard alongside your balance and usage stats.
- Sign up with Google for an instant $0.50 free trial
- Email-based accounts start with zero balance
- Keys are generated instantly and ready to use
First Request with cURL
Use this command to send text to the API. Replace YOUR_KEY with your actual token and adjust the voice or language as needed.
- POST https://api.playn57.com/v1/audio/speech
- Headers: Authorization: Bearer YOUR_KEY
- Body: {"model": "tts-1", "input": "Hello world", "voice": "nova"}
Using OpenAI SDK
The API mirrors the OpenAI speech endpoint structure. Simply update the base URL in your OpenAI SDK client to https://api.playn57.com/v1 and use your EchoPress key.
- Compatible with official OpenAI SDKs
- Change base_url to https://api.playn57.com/v1
- Use standard speech generation methods
API Endpoint
Send a POST request to https://api.playn57.com/v1/audio/speech to convert your article text into natural-sounding audio. This endpoint accepts JSON input and returns the generated audio file directly in the response, making it easy to integrate into your WordPress publishing workflow.
POST /v1/audio/speech
Use this endpoint to generate audio files from your text content. The API processes requests sequentially, so longer texts may take a few seconds. Ensure your text is under 4,096 characters per request to avoid splitting.
JSON Request Body
Include the text to be spoken in the input field. You must also specify a model (tts-1 or tts-1-hd) and a voice from the eight available presets. Optionally, set response_format, speed, and language for precise control.
- model: "tts-1" or "tts-1-hd"
- input: Your article text (max 4,096 chars)
- voice: e.g., "aria", "nova", "atlas"
- response_format: mp3, wav, opus, flac, or pcm
Response Format
Upon success, the API returns the audio file in the format you requested. Failed requests are free, and the charge is returned in full. The response includes the audio binary along with standard HTTP headers.
Request Parameters
Configure your synthesis requests by selecting the engine model, ensuring your input text stays within character limits, and choosing the appropriate voice and speed settings to match your article's tone.
Model Selection (tts-1, tts-1-hd)
Set the model to either "tts-1" or "tts-1-hd". Both options use the same underlying engine and incur identical pricing, so you can choose based on preference without worrying about cost differences.
Input Text Limit (4096 chars)
Each API request accepts up to 4096 characters of text, including spaces and punctuation. For longer articles, split your content into chunks of this size and join the resulting audio files to create a complete listening experience.
Voice and Speed Settings
Choose from eight distinct voices, ranging from the warm narration of Aria to the deep documentary style of Orion. Adjust the speed parameter between 0.25 and 4.0 to control the playback rate, allowing you to optimize listening time for your blog readers.
- 8 preset voices available
- Speed range: 0.25–4.0
- Language detection or explicit ISO code
Response Formats
The API returns audio as a binary payload in the response body, allowing you to save the file directly or stream it to your media library. Choose the format that best balances file size and quality for your WordPress media library or podcast feed.
All formats support the standard voice presets and speed settings defined in your request. The audio file is returned after synthesis completes; for long texts, generation takes roughly real-time duration (about 25 characters per second), so updates are not instantaneous.
MP3 Support
MP3 is the default and most widely supported format for web players. It offers excellent compression, making it ideal for embedding audio players in blog posts without slowing down page load times. Most WordPress themes and plugins support MP3 playback out of the box.
- Default format for web compatibility
- Small file size for faster loading
- Universal player support
WAV Format
WAV provides uncompressed, high-quality audio suitable for archival purposes or professional editing. Use this format if you need lossless quality for your audio blog or if your publishing workflow requires standard WAV files for further processing.
Note that WAV files are significantly larger than MP3s, which may increase bandwidth costs for high-traffic blogs.
- Lossless quality
- Larger file size
- Ideal for editing
OPUS, FLAC, PCM Options
OPUS offers superior compression at low bitrates, perfect for mobile data saving. FLAC provides lossless compression for high-fidelity archives. PCM is raw audio data, useful for direct processing in audio software.
Select the format that matches your storage constraints and listener device capabilities.
- OPUS: Efficient for mobile data
- FLAC: Lossless compression
- PCM: Raw audio data
Authentication
Authentication for the EchoPress API relies on a simple Bearer token scheme. You must include your unique API key in the HTTP header of every request to verify your account and track usage against your balance.
Bearer Token Usage
Include the header Authorization: Bearer tts-<your-key> in each POST request. The key is issued when you sign up and appears on your dashboard alongside your current balance and usage stats.
Key Rotation
You can generate a new API key at any time from your account dashboard. This is useful if you suspect your key has been exposed or if you want to rotate credentials for different blog plugins.
Single Active Key
Each account maintains only one active key. When you issue a new key, the previous one stops working immediately. Ensure your WordPress plugin or script is updated with the new token before the old one becomes invalid.

Rate Limits
EchoPress enforces a rate limit of 60 requests per minute per API key to ensure stable audio synthesis. This limit applies to all endpoints, including voice listing and model details. Managing your request volume helps avoid temporary throttling during peak publishing hours.
60 Requests Per Minute
The standard rate limit allows 60 requests per minute for authenticated accounts with a funded balance. This throughput is sufficient for most blog publishing workflows, including automated article-to-audio conversions. Exceeding this limit results in a 429 Too Many Requests error until the window resets.
- Limit: 60 requests/minute per key
- Applies to all API endpoints
- Resets on a sliding window basis
10 Requests Before Top-Up
New accounts without a top-up are limited to 10 requests per minute. This lower tier allows you to test the API during your free trial period without requiring immediate payment. Once you add USDT (TRC-20) to your balance, the limit increases to the standard 60 requests per minute.
- Unfunded accounts: 10 requests/minute
- Top-up required for higher limits
- Limits increase immediately after funding
Queue Handling
Requests are processed sequentially. If you send multiple requests rapidly, they may wait in a queue before synthesis begins. This ensures audio quality but may introduce slight delays during high-volume bursts. Plan your publishing schedule to distribute requests evenly throughout the minute.
- Sequential processing order
- Queuing occurs under high load
- Plan requests to minimize delays
Error Handling
Synthesis failures are free, so your balance remains intact even if a request fails. The API returns standard HTTP status codes to indicate success or specific error conditions, allowing your application to handle issues gracefully without unexpected charges.
Requests are processed sequentially, so under load a request may wait in a queue. Understanding the error codes helps you distinguish between transient network issues and permanent configuration errors, ensuring a smooth publishing workflow for your blog audio content.
Common Error Codes
Use 400 for invalid input, such as exceeding the 4096 character limit or using an unknown voice ID. A 401 error indicates an invalid or expired API key, while 429 signals that you have hit the rate limit of 60 requests per minute.
Any 5xx errors represent temporary server-side issues. Since failed requests are free, you do not lose credit when these errors occur, but you should log them to monitor service stability.
- 400: Bad Request (invalid parameters or input length)
- 401: Unauthorized (invalid API key)
- 429: Too Many Requests (rate limit exceeded)
- 500-503: Server Errors (temporary internal issues)
Handling Failures
When a request fails, check the HTTP status code and the error message in the response body. For 4xx errors, correct your parameters immediately, such as ensuring the voice ID exists in the /v1/voices list. For 5xx errors, the issue is on our end, but the request remains free.
Retry Logic
Implement exponential backoff for 429 and 5xx errors to avoid overwhelming the queue. Since short phrases take a few seconds to generate, waiting briefly between retries ensures the server can process your next request without further delays. Do not retry 4xx errors without modifying the request parameters.
- Retry on 429 with exponential backoff
- Retry on 5xx errors with delay
- Do not retry 4xx errors without parameter changes
Voices Endpoint
The GET /v1/voices endpoint provides a complete list of available voice presets, their supported languages, and the output formats you can choose from. This endpoint helps you verify which voices are active and compatible with your specific use case before generating audio.
You can also check the /v1/models endpoint to confirm the available models. Understanding the voice catalog ensures you select the right tone for your blog posts, whether it’s a warm narrator or a neutral news reader.
GET /v1/voices
Call this endpoint to retrieve the full catalog of voices. The response includes details on each voice preset, such as gender, tone description, and supported languages. This allows you to dynamically update your WordPress plugin or blog interface with available options.
Use this data to map user preferences to specific voice IDs. For example, you might offer a dropdown menu in your WordPress admin panel that lets authors preview or select their preferred voice for article audio versions.
- Returns a JSON list of all 8 voice presets
- Includes metadata for each voice’s tone and language support
- Updates when new voices are added
List Available Voices
EchoPress offers 8 distinct voice presets, ranging from warm narrators like Aria to neutral news readers like Atlas. Each voice is designed for specific content types, ensuring your audio articles match the tone of your written posts.
You can mix and match voices across different articles. For instance, use Luna for storytelling features and Felix for energetic promo posts. All voices support all 23 supported languages, allowing for multilingual content without needing separate voice setups.
Language Support Info
The API supports 23 languages, including English, Spanish, French, German, Chinese, Japanese, and more. Any voice can speak any of these languages, providing flexibility for international blogs.
If you do not specify a language, the system guesses it from the script (Latin text defaults to English). For non-English Latin-script text, always set the language parameter to ensure accurate pronunciation and tone.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Each voice is based on licensed recordings, ensuring high-quality audio that fits your content's tone.
23 languages
Any voice speaks any of these languages.
