Frequently asked questions
How do I get an API key?
Sign up on our /get-api-key/ page using Google or an email and password. Your account is specific to playd06.com. The dashboard displays your active key, balance, and usage details. You can issue a new key at any time, which immediately invalidates the old one.
Can I use the OpenAI SDK?
Yes. Our API uses the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDKs by simply changing the base_url to https://api.playd06.com/v1 and providing your VocalRead key. This allows for easy integration into your existing Python or Node.js workflows.
What is the base URL?
The API base URL is https://api.playd06.com/v1. You send POST requests to /v1/audio/speech for synthesis. Other endpoints include GET /v1/voices for available options and GET /v1/models for model details. Ensure your SDK or HTTP client points to this specific domain for all requests.
How do I handle errors?
Failed requests are free; if synthesis fails, the charge is returned in full. You should check the HTTP response status code. If an error occurs, your balance remains unaffected. Review the error message in the response body to understand if it was a rate limit or input issue.
What is the character limit?
Each request supports up to 4096 characters in the input field. Spaces and punctuation count toward this limit. For longer texts, you must split the content into chunks of 4096 characters or less, generate audio for each, and then join the resulting audio files programmatically.
Can I stream audio?
No. We do not support streaming, WebSocket connections, or real-time partial audio delivery. The API returns the complete audio file upon successful synthesis. You must wait for the full response before processing or playing the audio, which typically takes roughly real-time duration for long texts.
Does it support SSML?
No. Our API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You control the output only through the eight voice presets and the speed parameter (0.25–4.0). For precise control, adjust the input text directly rather than relying on markup tags within the payload.
How do I change my voice?
Change the voice by updating the voice parameter in your request body. We offer eight presets: aria, nova, luna, sage, felix, milo, atlas, and orion. Each voice can speak any of our 23 supported languages. Select the preset that best fits your educational content style.
What is the response format?
You can choose from mp3, wav, opus, flac, or pcm using the response_format field. The API returns the audio file directly in the response. These formats cover most educational use cases, from web playback to high-quality archival. Select the format that matches your application's audio player capabilities.
Is there a Python example?
Yes. Since our endpoint matches the OpenAI speech API shape, you can use the official OpenAI Python SDK. Set the base_url to https://api.playd06.com/v1 and use your API key. Send a POST request to /v1/audio/speech with your text, voice, and format parameters to generate audio.
How do I split long texts?
Split your text into parts of up to 4096 characters. Send each part as a separate POST request to the speech endpoint. Once you receive the audio files for each chunk, join them sequentially in your application. This ensures you stay within the single-request character limit.
What happens if I exceed limits?
You are limited to 60 requests per minute per key. If you exceed this, requests may queue or fail. Before your first top-up, the limit is 10 requests per minute. Failed requests do not consume your balance, but successful ones are charged at $0.01 per 1,000 characters.
Is authentication secure?
Yes. We use standard Bearer token authentication. Include your key in the Authorization header as 'Bearer tts-...'. Each account has one active key. You can issue a new key anytime, which immediately stops the old one, ensuring that lost keys cannot be used to access your account.
Can I use multiple keys?
No. Each account has only one active API key at a time. If you issue a new key, the previous one stops working immediately. This simplifies security management. You do not need to manage multiple keys for different environments or users within the same account.
First request
curl
curl https://api.playd06.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.playd06.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.playd06.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 |
Get Your API Key
Sign up for a free account on playd06.com using your Google account or a standard email and password. This gives you immediate access to a $0.50 trial credit (valid for 7 days), enough for about 50,000 characters of audio generation. Your account is created instantly, allowing you to start building audio lessons or reading materials for your students without any enterprise contracts or waiting periods.
Sign up with Google or email
Creating an account is straightforward. You can register via Google for quick access or use a traditional email and password method. Note that accounts created with email and password do not receive the initial trial credit, so Google sign-in is recommended for immediate testing. Once registered, your account is ready to accept API requests.
- Google Sign-In provides $0.50 trial credit (valid for 7 days)
- Email/Password accounts start with zero balance
- No credit card required to begin
Find your key on the dashboard
After logging in, navigate to the /get-api-key/ page to view your unique API key. The dashboard displays your current balance, remaining characters, and a ready-to-use cURL example for quick testing. Your key is formatted as 'tts-...' and is the only credential needed to authenticate your requests to the API.
- Access your key at /get-api-key/
- View real-time balance and character usage
- Copy the key starting with 'tts-'
Keep your key secure
Your API key authenticates all your requests, so treat it like a password. You can issue a new key at any time from your dashboard, which instantly invalidates the old one. This allows you to rotate keys if you suspect a leak or need to reset access for different team members without losing your account data.
- Issue a new key to invalidate the old one instantly
- Store the key in environment variables for security
- One active key per account
Make Your First Request
Testing the API with curl is the fastest way to verify your setup. Use the provided example to send a simple text string and receive an audio file immediately. This method requires no additional libraries, making it perfect for quick validation before integrating into your lesson plans.
Use curl for quick testing
Run the command below, replacing YOUR_API_KEY with your secret key. The request sends a short phrase to the tts-1 model and saves the output as an MP3 file. This confirms your authentication and connectivity are working correctly before you process longer educational texts.
Send text and receive audio
The API accepts up to 4096 characters per request. Send your text in the input field and specify your preferred voice and language. The service processes the request synchronously, returning the audio file directly in the response body. This simplicity allows you to generate reading materials without complex workflow setups.
- Set
modeltotts-1ortts-1-hd - Include text in the
inputfield - Select a voice from the 8 presets
Check response format
Upon success, the response contains the raw audio bytes in your chosen format. If the synthesis fails, the charge is returned in full, and the response includes an error code. Always check the HTTP status code to ensure the audio was generated correctly before saving the file.
Use with OpenAI SDK
VocalRead is designed for easy migration. Since our API follows the same request shape as the OpenAI Speech endpoint, you can keep your existing code structure and simply point your SDK to our servers. This means teachers and methodologists can integrate synthetic speech into lesson plans without rewriting complex logic or learning a new library.
Change base_url to our API
Update your SDK configuration to use https://api.playd06.com/v1 as the base URL. Your existing tts-1 or tts-1-hd model calls will work immediately. This single change routes requests to our infrastructure while maintaining compatibility with standard TTS workflows.
- Base URL: https://api.playd06.com/v1
- Models: tts-1, tts-1-hd
- Standard JSON body structure
Use official SDKs
You do not need a custom library. The official OpenAI SDKs handle the communication perfectly. This allows you to leverage well-documented, stable client libraries that are already familiar to many developers. It ensures reliable handling of audio responses and error states.
Supports Python and Node.js
Both Python and Node.js environments are fully supported. You can generate audio files for educational materials using your preferred language. The SDKs manage the HTTP requests and audio data conversion seamlessly, letting you focus on content creation rather than infrastructure details.
Supported Audio Formats
The API supports multiple audio formats to suit different educational use cases, allowing you to choose the best balance between file size and quality for your classroom materials. Each format is optimized for specific workflows, from quick web playback to high-fidelity archiving.
You can specify the desired format in your request using the response_format parameter. Supported options include MP3, WAV, OPUS, FLAC, and PCM, giving you full control over how your generated audio lessons are stored and delivered.
MP3 for web playback
MP3 is a versatile choice for embedding audio directly into learning management systems or web-based reading materials. Its small file size ensures fast loading times for students accessing lessons on various devices, making it ideal for everyday classroom use.
- Optimized for web browsers and mobile apps
- Small file size for quick streaming
- Universal compatibility with standard media players
WAV for high quality
WAV provides uncompressed, high-fidelity audio. This format is perfect for creating master copies of lessons that will be further edited or distributed in professional educational contexts.
- Lossless quality for professional standards
- Ideal for archival and editing
- No compression artifacts
OPUS and FLAC for archiving
For long-term storage of extensive course libraries, OPUS and FLAC offer excellent compression without sacrificing audio integrity. FLAC is lossless, while OPUS provides high efficiency at lower bitrates, both ensuring your educational resources remain accessible for years.
- FLAC for lossless archival
- OPUS for efficient compression
- Suitable for large-scale storage
Rate Limits and Speed
Understanding rate limits and generation speed helps you plan your audio lesson workflows efficiently. Our API processes requests sequentially, meaning under heavy load, synthesis may wait in a queue. This ensures stable performance for your teaching materials without unexpected failures.
60 requests per minute
Once you have topped up your account, you can make up to 60 requests per minute. This limit applies per API key, allowing you to generate multiple audio files quickly for a single class or lesson set.
10 requests before top-up
Before your first top-up, you are limited to 10 requests per minute. This allows you to test the API thoroughly. Top-ups via USDT (TRC-20) are processed automatically within minutes, instantly increasing your limit to 60 requests per minute.
Real-time generation speed
Generation speed is roughly real-time, averaging about 25 characters of text per second of audio. Short phrases may take a few seconds to process. Longer texts are split into 4096-character chunks and joined, maintaining a natural flow for your students.

Handling Long Texts
Text-to-speech requests have a strict limit of 4096 characters per call. For longer lessons or reading materials, you must split the input text into smaller chunks to ensure successful synthesis.
Once each chunk is processed, the API returns individual audio files. You can then concatenate these files into a single continuous audio track for your students.
Split text into 4096 chars
Divide your source text into chunks of up to 4096 characters. Spaces and punctuation count toward this limit, so ensure your splitting logic accounts for them.
Join audio files
Each request returns an audio file in your chosen format. Combine these files sequentially to reconstruct the full lesson audio without gaps or overlaps.
Manage chunking logic
Implement simple logic in your script to handle text splitting. This ensures that sentences or paragraphs are not broken awkwardly in the middle, maintaining a natural listening experience for your students.
Common Errors
Even when your code is correct, specific limits and input constraints can cause failures. Understanding these common errors helps you debug quickly and keep your audio generation pipeline running smoothly.
This guide covers authentication issues, throughput caps, and character limits so you can handle edge cases without interrupting your lesson creation workflow.
Invalid API key
If the API returns a 401 error, your token is missing, expired, or incorrect. Ensure you copy the key exactly from your dashboard at /get-api-key/.
Remember that issuing a new key immediately invalidates the old one. If you switch keys, update your application configuration instantly to avoid service interruptions.
- Check for trailing spaces when copying keys.
- Verify the 'Bearer' prefix is included in the Authorization header.
Rate limit exceeded
You are limited to 60 requests per minute per key. If you exceed this, the API returns a 429 error. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed.
Implement exponential backoff in your script to handle these temporary blocks gracefully without overwhelming the server.
- Limit: 60 req/min after top-up.
- Limit: 10 req/min for new accounts.
Text too long
Each request accepts a maximum of 4096 characters in the input field. If your text exceeds this, the API will reject the request.
Split your long texts into chunks under 4096 characters, generate audio for each, and concatenate the resulting files for the final lesson audio.
- Max input length: 4096 characters.
- Include spaces and punctuation in the count.
Authentication Details
Authentication for the VocalRead API relies on a single, active API key per account. You retrieve this key from your dashboard after signing up via Google or email. It is essential to keep this credential secure, as it grants full access to your account’s billing and usage data.
Bearer token format
Include your key in the HTTP header using the standard Bearer scheme. The header must appear exactly as Authorization: Bearer tts-... for every request. This format ensures the API correctly identifies your account and applies your current rate limits and balance.
One active key per account
Each account maintains only one active API key at any given time. This simplifies security management by eliminating the need to track multiple credentials across different environments or team members.
Revoke old keys instantly
If you suspect your key has been exposed, you can issue a new key from the dashboard. The old key stops working immediately, ensuring no unauthorized usage continues while you update your applications.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. However, its pricing structure can become complex and expensive as usage scales, often requiring careful monitoring to avoid unexpected costs.
23 languages
Any voice speaks any of these languages.
