Frequently asked questions
How do I get an API key?
Sign up at /get-api-key/ using Google or email. You receive one active key per account. You can issue a new key anytime, which instantly invalidates the old one. The dashboard displays your key, balance, and usage stats immediately after creation.
What is the base URL for the API?
The base URL is https://api.playuk9.com/v1. You send POST requests to /audio/speech for synthesis and GET requests to /voices or /models. This endpoint structure matches the OpenAI speech endpoint, allowing you to use existing OpenAI SDKs by simply changing the base URL.
Can I use the OpenAI SDK?
Yes. The API uses the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDKs by updating the base_url to https://api.playuk9.com/v1 and providing your site-specific API key. This allows seamless integration with your existing codebase.
How many voices are available?
We offer 8 preset voices: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. Each voice can speak any of the 23 supported languages, giving you flexible options for your YouTube content. Whether you need a warm narrator or a deep documentary tone, these licensed recordings cover a wide range of styles for your videos.
What audio formats are supported?
You can choose from mp3, wav, opus, flac, or pcm. Select the format that best fits your YouTube workflow. MP3 and Opus are efficient for web delivery, while WAV and FLAC offer high quality. PCM is available for raw audio processing needs.
What are the rate limits?
You are limited to 60 requests per minute per key. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed. This ensures fair usage across the network. Monitor your dashboard to stay within these limits.
What happens if I exceed the rate limit?
Requests are processed sequentially. If you exceed the limit, subsequent requests may wait in a queue or return an error. Failed requests do not consume credits. To maintain throughput, consider implementing exponential backoff in your application logic when handling rate limit errors.
How do I handle errors?
Check the HTTP status code in the response. If synthesis fails, the charge is returned in full. Ensure your input text is under 4096 characters and your API key is valid. Use the /v1/voices endpoint to verify available voices and languages before making requests.
What is the character limit per request?
Each request supports up to 4096 characters of input text. Spaces and punctuation count toward this limit. For longer scripts, split your text into chunks of 4096 characters or less. Generate audio for each chunk separately and join the files for your final video.
How do I split long texts?
Divide your script into segments of up to 4096 characters. Send each segment as a separate POST request to /audio/speech. Receive the audio files for each chunk and concatenate them using your preferred audio editor. This ensures consistent quality and avoids hitting character limits.
Is the API RESTful?
Yes. The API uses standard HTTP methods. Use POST for generating speech and GET for retrieving voices or models. It follows standard REST conventions, making it easy to integrate with any programming language or tool that supports HTTP requests and JSON data exchange.
Do I need to install any libraries?
No specific library is required. You can use plain HTTP requests or the official OpenAI SDK. Since the API matches the OpenAI speech endpoint shape, simply adjust the base URL to https://api.playuk9.com/v1. Note that no mobile SDK or WordPress plugin is provided, so you will need to handle integration directly in your code.
Can I use custom headers?
Yes. You must include the Authorization: Bearer tts-... header with your API key. Other custom headers are not required, but standard HTTP headers like Content-Type are supported. Ensure your key is passed correctly to authenticate each request to the API.
How do I test the API?
Use the ready curl example on your /get-api-key/ dashboard. Send a small text payload to the POST /v1/audio/speech endpoint. Check the response for the audio file or error details. Verify your balance and key validity before processing larger volumes of text for your videos.
First request
curl
curl https://api.playuk9.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.playuk9.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.playuk9.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 at https://playuk9.com/get-api-key/ using Google to instantly receive $0.50 in trial credit, valid for 7 days. Email-based accounts start without this bonus. Once registered, your dashboard displays your active API key, current balance, and a ready-to-use curl example for immediate testing.
Generate a New Key
Access your unique key directly from the dashboard. You can generate a new key at any time without waiting for expiration. This new key becomes active immediately, allowing you to rotate credentials easily if needed.
Revoke Old Keys
Revoking is automatic. When you issue a new key, the previous one stops working instantly. There is no waiting period or manual deactivation step required, ensuring your old credentials cannot be used for new requests.
Manage Your Access
The dashboard provides a clear view of your current key, character usage, and billing status. You do not need to navigate complex settings menus to find your authentication token or check your remaining trial balance.
- View active key and balance instantly
- Issue new key to invalidate old one
- Track character usage in real time
Quickstart with Curl
This section shows how to generate speech using curl, the standard command-line tool. You send a JSON payload containing your text, voice selection, and model choice to the API endpoint. The server returns the audio file directly, allowing you to save it for editing in your YouTube workflow.
Authentication is handled via a Bearer token in the HTTP headers, while the request details live in the JSON body. This separation keeps your API key secure and your text data clearly structured for easy debugging and scripting.
Basic Request Example
Send a POST request to https://api.playuk9.com/v1/audio/speech with a JSON body. Replace YOUR_API_KEY with your actual key. The input field holds your script, and voice selects a preset like aria or nova.
```bash curl -X POST https://api.playuk9.com/v1/audio/speech \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "tts-1", "input": "Hello world", "voice": "nova", "response_format": "mp3"}' \ -o audio.mp3 ```
Headers and Auth
The Authorization header must contain your Bearer token (Bearer tts-...). The Content-Type must be set to application/json. These headers are separate from the JSON payload, which contains the model, input, voice, response_format, and optional speed or language fields.
Ensure your API key is active and has sufficient balance. Failed requests return no charge, so you can safely test headers without worrying about credits.
Response Format
A successful response returns the audio file directly in the body, with the appropriate Content-Type (e.g., audio/mpeg for MP3). You can redirect this output to a file using curl -o output.mp3. If the request fails, you will receive a JSON error object with a code and message, helping you debug issues like invalid voices or rate limits.

Using the OpenAI SDK
The official OpenAI SDKs work seamlessly with our API by simply changing the base_url. This allows you to use familiar Python or Node.js code without learning a new library. You only need to point the client to our API base URL and provide your VoiceBloom API key for authentication.
Set Base URL
Initialize your OpenAI client with the base URL https://api.playuk9.com/v1. Ensure you set the api_key to your unique VoiceBloom key. This directs all requests to our synthesis endpoint instead of OpenAI’s servers.
- Base URL:
https://api.playuk9.com/v1 - Auth Header:
Authorization: Bearer tts-...
Import the Library
Install the standard openai package via pip or npm. The SDK handles JSON serialization and HTTP requests automatically. You do not need a custom SDK from VoiceBloom; the existing OpenAI client structure is fully compatible with our endpoints.
Make Your First Call
- Model:
tts-1ortts-1-hd - Format:
mp3(default) orwav
Supported Voices
We provide eight preset voices built from licensed LibriTTS-R recordings and public-domain LibriVox readings. Each voice offers a distinct tone, allowing you to match the mood of your YouTube content without hiring voice actors or engineers. All generated audio includes an inaudible synthetic watermark to mark it as AI-generated speech.
Aria and Nova
Aria delivers a warm, clear narration style suitable for educational content. Nova offers a bright, upbeat tone that works well for fast-paced videos or promotional segments.
Luna and Sage
Luna features a soft, storytelling style that is excellent for video essays or calm backgrounds. Sage provides a calm, instructional tone, making it ideal for how-to guides and step-by-step explanations.
Felix and Milo
Felix brings energetic, promo-style energy to your content. Milo provides a friendly, conversational voice that feels natural for vlogs and direct-to-camera segments.
Audio Formats
We support five standard audio formats to suit your YouTube workflow. MP3 is the industry standard for web playback, while WAV provides uncompressed quality for professional editing in tools like Premiere or DaVinci Resolve.
MP3 and WAV
Choose MP3 for efficient file sizes that upload quickly to YouTube. Select WAV if you need lossless audio for high-quality post-production or voiceover mixing.
OPUS and FLAC
OPUS offers efficient compression suitable for streaming applications. FLAC provides lossless compression, reducing file size without sacrificing audio integrity.
PCM Support
PCM returns raw, uncompressed audio data for maximum compatibility with legacy systems or specific encoding pipelines.

Rate Limits
Rate limits protect the service from queueing delays. New accounts start with 10 requests per minute. After your first USDT top-up is credited, the limit increases to 60 requests per minute.
Requests are processed sequentially, so longer texts may wait in a queue during high load. Exceeding the limit returns an error without charging your balance.
60 Requests Per Minute
Once your USDT transfer is confirmed, you get 60 requests per minute. This handles most YouTube production needs without significant delays.
Initial Limit of 10 RPM
Accounts without a top-up are limited to 10 requests per minute. This prevents server overload while you test the API.
Limit Increases After Top-Up
The limit automatically increases to 60 RPM after your first USDT (TRC-20) top-up is credited. No manual verification step is required.
Use the 10 RPM limit to test your workflow. Once you add funds, your capacity scales immediately for your video projects.
- Top-ups are credited within minutes
- No monthly plans or subscriptions
- Balance never expires
Handling Errors
When your API call fails, the response includes an HTTP status code to help you identify the issue. Understanding these codes allows you to fix problems quickly without wasting credits, as failed requests are free.
Common Error Codes
A 401 Unauthorized error means your API key is missing or invalid. Ensure you are sending the correct Authorization: Bearer header. A 429 Too Many Requests error indicates you have hit your rate limit. New accounts start with a limit of 10 requests per minute, which increases to 60 RPM after a top-up. If you see this, wait a moment or add credit to your account.
- 400: Bad Request – Check your JSON structure or input length.
- 401: Unauthorized – Verify your API key is correct.
- 429: Too Many Requests – You have exceeded your current RPM limit.
Retry Logic
Implement exponential backoff in your code. Start with a short delay (e.g., 1 second) and double it for each retry. This prevents overwhelming the server during temporary load spikes. Since requests are processed sequentially, brief pauses help ensure your next request is handled efficiently.
Debugging Tips
Always check the input field length. The API accepts up to 4096 characters per request. If your text is longer, split it into chunks before sending. Also, verify that the model and voice values match the supported presets. Use the /v1/voices endpoint to confirm available voices and languages if you are unsure about support for specific scripts.
Character Limits
The API enforces a strict limit of 4096 characters per request. If your script exceeds this, you must split the text into smaller parts. Generate audio for each part separately, then join the resulting audio files in your video editing software.

Character Limits
Each API request accepts up to 4096 characters of input text. This limit includes all spaces, punctuation, and special symbols. If your script exceeds this, the synthesis will fail, so you must split longer scripts into smaller chunks before sending them to the endpoint.
You can split your text into parts of up to 4096 characters and join the resulting audio files. This ensures you never hit the character cap while maintaining the flow of your narration for YouTube videos.
Splitting Long Texts
Divide your script into segments of 4096 characters or fewer. Send each segment as a separate POST request to the speech endpoint. Since requests are processed one after another, ensure your script handles the output files in order.
- Count characters including spaces and punctuation.
- Split at natural sentence breaks where possible.
- Send requests sequentially to maintain order.
Audio Joining
After receiving the audio files for each segment, concatenate them to form the final narration. This method allows you to handle long YouTube scripts without worrying about character limits per request.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Create stunning videos with ease using our intuitive platform designed for creators.
23 languages
Any voice speaks any of these languages.
