Frequently asked questions
How do I get an API key?
Sign up at /get-api-key/ via Google or email. Your account is specific to playdd555.com. The dashboard immediately displays your active API key, balance, and usage statistics, allowing you to start making requests without delay. Note that accounts created with email and password do not receive the free trial credit, which is only granted for Google sign-ins.
What is the base URL for the API?
The API base URL is https://api.playdd555.com/v1. You send POST requests to /audio/speech and GET requests to /voices or /models. This endpoint structure matches the OpenAI speech endpoint, ensuring compatibility with standard HTTP clients and SDKs.
Can I use the OpenAI SDK?
Yes, the official OpenAI SDKs work by changing the base_url to https://api.playdd555.com/v1 and using your site-specific key. You do not need a custom SDK. Standard HTTP requests also work directly with the JSON body format.
How do I handle rate limits?
You are limited to 60 requests per minute per key. New accounts start with 10 requests per minute until the first top-up. Requests are processed sequentially, so under load, a request may wait in a queue before generating audio.
What formats are supported?
Supported response formats are mp3, wav, opus, flac, and pcm. Specify the desired format in the request body using the response_format field. The API returns the audio file directly in the response according to the format you selected.
How do I split long texts?
Split your input text into parts of up to 4096 characters. Send each part as a separate request and join the resulting audio files. This ensures compliance with the character limit per request while allowing you to generate longer content.
What is the speed range?
The speed parameter accepts values between 0.25 and 4.0. Adjusting speed changes the playback rate of the generated audio. This allows you to fine-tune the voice output for different content types, such as slower narration or faster dialogue.
Do I need to specify the language?
It is optional. If omitted, the language is guessed from the script, defaulting to English for Latin text. For non-English Latin-script text, you should explicitly set the language parameter to ensure accurate synthesis and avoid misinterpretation by the engine.
How are errors returned?
Errors are returned via standard HTTP status codes and JSON error objects. Failed requests are free, and the charge is returned in full if synthesis fails. You should check the response status to determine if the request succeeded or failed.
Is the API synchronous?
Yes, the API is synchronous. You send a request and receive the audio file in the response. There is no WebSocket or streaming endpoint. You must wait for the full audio generation to complete before receiving the file data.
What is the character limit per request?
Each request supports up to 4096 characters in the input field. Spaces and punctuation count toward this limit. For texts longer than 4096 characters, you must split the text into multiple requests and concatenate the resulting audio files.
How do I rotate my API key?
You can issue a new API key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. This allows you to revoke access or refresh credentials without downtime for your application.
Can I use multiple keys?
Each account holds one active key, but you can issue a new key at any time. The previous key stops immediately upon rotation. To use multiple keys concurrently, create separate accounts, each with its own key and balance. This allows you to manage distinct use cases or split usage across independent API keys without waiting for rotation.
What happens if the server is down?
The API does not offer an SLA or uptime guarantee. If the service is unavailable, requests fail but remain free, with any charges returned in full. Since there is no on-premise option or data-center choice, you cannot host the engine yourself to mitigate downtime. Support is available via email if issues persist.
How do I decode the audio response?
The API returns the audio file directly in the response body. The format depends on your response_format setting (mp3, wav, opus, flac, pcm). You can save the response body directly as an audio file or process it using standard binary handling.
Is SSML supported?
No, SSML is not supported. The API accepts plain text input only. You cannot use SSML tags for pronunciation, pauses, or prosody control. You must rely on the voice presets and speed parameters to adjust the audio output characteristics.
Can I stream the audio?
No. The API returns the complete audio file in a single synchronous response, so there is no WebSocket or real-time partial audio streaming. You must wait for the full file before playing or processing it. For long texts, split the input into parts of up to 4096 characters and join the resulting audio files manually.
What is the model ID?
The model IDs are tts-1 and tts-1-hd. Both use the same engine and price. You can choose either model ID in your requests. The choice does not affect the cost, which is $10 per 1 million characters.
First request
curl
curl https://api.playdd555.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.playdd555.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.playdd555.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 |
Authentication
Access the API by generating a key via the /get-api-key/ page. You can sign in with Google or use email and password. The key appears immediately on your dashboard alongside your balance and usage statistics.
Include the key in every request header. Use a single active key per account. You can issue a new key at any time. The old key stops working immediately upon creation of the new one.
Obtain Your API Key
Navigate to /get-api-key/ to create an account. Choose Google Sign-In for immediate trial credit ($0.50) or use email/password. Your unique API key appears immediately on the dashboard alongside your balance and usage stats.
Bearer Token Usage
Send the key in the Authorization header of every request. Format: Authorization: Bearer tts-.... This token authenticates your account and tracks usage against your balance.
Key Management and Rotation
You can issue a new key at any time from the dashboard. The new key becomes active immediately. The old key stops working at once. Ensure your application updates the header value to avoid failures.
Endpoints Overview
The API exposes three primary endpoints for managing your text-to-speech integration. The speech generation endpoint handles audio synthesis, while the voices and models endpoints provide metadata about available options. All requests use standard JSON bodies and return structured data.
These endpoints allow developers to dynamically fetch available voices and formats without hardcoding values. This flexibility supports rapid prototyping and ensures your application stays aligned with the current engine capabilities.
Speech Generation Endpoint
Send text to POST https://api.playdd555.com/v1/audio/speech to receive an audio file. The endpoint accepts a JSON body with fields like model, input, voice, and response_format. It mirrors the OpenAI speech endpoint structure, allowing you to use existing SDKs by simply adjusting the base URL.
Ensure your input text does not exceed 4096 characters. The API processes requests sequentially, so long texts should be split and joined client-side for optimal performance.
- Method: POST
- URL: /v1/audio/speech
- Body: JSON with model, input, voice
Voices List Endpoint
Query GET https://api.playdd555.com/v1/voices to retrieve a list of available voice presets, supported languages, and audio formats. This endpoint helps you discover options like aria, nova, luna, sage, felix, milo, atlas, and orion without hardcoding them into your application.
The response includes metadata about each voice, such as gender and tone descriptors, aiding in quick selection for your specific use case.
- Method: GET
- Returns: Voice presets, languages, formats
Models Endpoint
Use GET https://api.playdd555.com/v1/models to list available TTS models. Currently, this includes tts-1 and tts-1-hd, which share the same engine and pricing but offer different quality tiers.
This endpoint ensures your application can dynamically adapt to any new models released by the provider, maintaining compatibility without code changes.
- Method: GET
- Returns: Available model IDs

First Request with cURL
Send a POST request to the speech endpoint with your JSON payload. The API processes the text and returns the synthesized audio file directly in the response body. There is no streaming; you receive the complete audio file upon completion.
Basic JSON Body Structure
Construct a JSON object containing the model, input text, voice selection, and desired response format. Ensure the text does not exceed 4096 characters. The request must include the audio format you prefer, such as mp3 or wav.
Required Parameters
The model field accepts "tts-1" or "tts-1-hd". The input field holds your text string. Specify voice from the eight available presets and response_format from mp3, wav, opus, flac, or pcm. The Authorization header must carry your Bearer token.
Example Response
A successful response returns the audio binary data. Failed requests return an error JSON and no charge. You can save the returned bytes directly to a file or pass them to your application’s audio player for playback.
OpenAI SDK Compatibility
Our API mirrors the OpenAI speech endpoint structure, allowing you to leverage official OpenAI SDKs by simply changing the base_url to https://api.playdd555.com/v1. This compatibility means you can integrate our text-to-speech engine without rewriting your client logic or adopting a new library.
Configuring base_url
To connect, update your SDK configuration to point to our API base URL. The request shape remains identical to OpenAI’s, so existing code for sending text and receiving audio files works immediately with our endpoint.
Using Official SDKs
You can use the standard OpenAI Python or Node.js libraries. Ensure you pass your unique tts-... API key in the Authorization header. The SDK handles the JSON body structure, including model, voice, and input text.
- Supports tts-1 and tts-1-hd models
- Handles JSON body serialization automatically
- Uses standard Bearer token authentication
Migration Steps
Switching from OpenAI to DevTTS requires only two changes: update the base URL and replace the API key. No changes to the voice parameter names or response parsing are needed. Your application continues to receive audio files in the specified format.
Response Formats
The API returns audio files in the format specified by your response_format parameter. Each request generates a single, self-contained audio file that you download and store. There is no streaming delivery or WebSocket connection; you receive the complete file upon successful synthesis.
MP3 Output
MP3 is the default format and offers a good balance between file size and quality. It is widely supported by web players, mobile apps, and most development frameworks. Use this format for general-purpose applications where storage efficiency matters.
WAV Output
WAV provides uncompressed audio data, preserving the full fidelity of the synthesis engine. This format is ideal for professional workflows, archival purposes, or when you need to process the audio further without decoding artifacts. Note that WAV files are significantly larger than MP3s.
Opus, FLAC, and PCM Options
Opus delivers efficient compression with high quality, suitable for modern web standards. FLAC offers lossless compression, reducing file size without sacrificing audio integrity. PCM provides raw, uncompressed audio samples, useful for low-level audio processing or specific hardware integrations.

Error Handling
The API returns standard HTTP status codes to indicate success or failure. A 400 error typically means your request body is malformed or missing required fields, such as an invalid voice name. A 500 error indicates a temporary server-side issue. Failed synthesis requests are free, so you are not charged for these errors.
Common Error Codes
400 Bad Request: Check your JSON structure and ensure all required fields like model and input are present. 401 Unauthorized: Your API key is missing or invalid. 500 Internal Server Error: The service encountered a temporary issue; retry after a short delay.
Rate Limit Errors
You receive a 429 Too Many Requests error when exceeding 60 requests per minute. New keys start with a limit of 10 requests per minute until the first top-up is processed. The API processes requests sequentially, so high load may cause queuing delays before you hit the limit.
Retry Strategies
Implement exponential backoff for 429 and 500 errors. Since requests are queued under load, immediate retries may fail again. Wait for the specified Retry-After header if provided, then retry. Failed requests do not consume your character balance, so no credit is lost during retries.
Rate Limits
Rate limits protect API stability and ensure fair usage across all accounts. Each API key is capped at 60 requests per minute once your account is active and funded.
60 Requests Per Minute
After your initial trial or first top-up, your key allows 60 requests per minute. This limit applies per key, so you can scale by rotating keys if needed.
Initial Limit for New Keys
New keys start with a lower limit of 10 requests per minute. This applies until you complete your first top-up, which automatically increases your quota to the standard 60 requests per minute.
Queue Behavior Under Load
Requests are processed sequentially. Under heavy load, a request may wait in a queue before synthesis begins. While typical generation speed is roughly real-time, queue wait times add to the total duration.

Advanced Usage
The API limits each request to 4,096 characters. For longer narratives, split the input text into chunks, generate audio for each segment, and concatenate the resulting files. This ensures reliable synthesis without truncation.
Adjust playback speed between 0.25 and 4.0 to fit your content’s pacing. Note that longer texts generate at roughly real-time speed, while short phrases may take a few seconds due to queue processing.
Splitting Long Texts
Send multiple requests for texts exceeding 4,096 characters. Receive individual audio files for each chunk. Concatenate these files client-side to reconstruct the full audio stream seamlessly.
- Max 4,096 characters per request
- Concatenate outputs client-side
Speed Control (0.25–4.0)
Use the speed parameter to adjust voice tempo. Values below 1.0 slow down narration, while values above 1.0 accelerate it. Ideal for audiobooks or quick updates.
- Range: 0.25 to 4.0
- Default speed applies if omitted
Language Code Specification
Provide an ISO language code (e.g., 'de', 'fr') to ensure accurate pronunciation, especially for Latin-script non-English text. Without it, the system guesses the language, defaulting to English for Latin scripts.
- Optional ISO code
- Guessed from script if omitted
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. indie developers build creative startups with limited budgets but massive ambition
23 languages
Any voice speaks any of these languages.
