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. Once registered, your dashboard displays your unique API key, balance, trial status, characters left, and usage. You can issue a new key at any time, which immediately invalidates the previous one.
Can I use the OpenAI SDK with this API?
Yes. Our endpoint shape matches the OpenAI speech endpoint exactly. Simply update your SDK’s base_url to https://api.play67bd.com/v1 and use your ScribbleVoice key. This allows you to use the official OpenAI SDKs without writing custom HTTP clients or handling complex authentication logic.
What is the base URL for the API?
The API base URL is https://api.play67bd.com/v1. You will use this endpoint for all your requests, including sending text for synthesis and retrieving available voices. Ensure your SDK or HTTP client is configured to point to this specific domain for correct routing.
How do I authenticate requests?
Include your API key in the Authorization header of every request. The format must be: Authorization: Bearer tts-... Your key is generated when you sign up. Keep this key secure, as it grants access to your account and allows you to consume your character balance.
What formats are supported?
You can request audio in mp3, wav, opus, flac, or pcm formats. Specify your preferred format using the response_format field in your JSON body. This flexibility allows you to choose the best balance between file size and quality for your specific integration needs.
How many characters can I send?
Each request supports up to 4096 characters of input text. If your content exceeds this limit, you must split the text into smaller chunks, generate audio for each part, and then join the resulting audio files. Spaces and punctuation count toward this character limit.
What happens if I exceed the rate limit?
The API allows 60 requests per minute per key (10 per minute before your first top-up). Requests are processed sequentially, so exceeding the limit may cause your request to wait in a queue. If synthesis fails, you are not charged for that request.
How do I handle errors?
If synthesis fails, the API returns an error response and the charge is returned in full to your balance. You can monitor your usage and status via the dashboard. Ensure your input text is under 4096 characters and your key is valid before retrying.
Can I rotate my API key?
Yes, you can issue a new API key at any time from your dashboard. When you generate a new key, the old one stops working immediately. This allows you to securely rotate credentials without downtime, ensuring that only your current application uses the active key.
Does the API support streaming?
No, the API does not support streaming, WebSockets, or real-time partial audio. You send a text payload and receive the complete audio file in the response. This synchronous approach simplifies integration for most use cases.
Is SSML supported?
No, the API does not support SSML or phoneme dictionaries. You provide plain text input, and the engine handles pronunciation automatically. If you need specific pronunciation control, you may need to adjust the text manually or use the speed and voice parameters to influence delivery.
How do I specify the language?
Include the language field with an ISO code in your request. If omitted, the system guesses the language from the script, defaulting to English for Latin text. For non-English Latin-script text, explicitly setting the language ensures accurate synthesis and prevents misinterpretation by the engine.
What is the default voice?
The documentation does not specify a single default voice name, but you must provide a voice parameter from the eight available presets. These include female voices like Aria and Nova, and male voices like Felix and Milo. You can list all available voices via the /v1/voices endpoint.
How do I check my usage?
Visit the /get-api-key/ page to view your dashboard. It displays your current balance, trial status, characters remaining, and detailed usage history. This data helps you monitor consumption against your $10 per million characters pricing model and plan your top-ups accordingly.
First request
curl
curl https://api.play67bd.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.play67bd.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.play67bd.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
Start by visiting /get-api-key/ to create your account. This is the single entry point for accessing the ScribbleVoice API, where you will manage your credentials and monitor usage without any complex setup steps.
Sign up on /get-api-key/
Navigate to the registration page to initialize your account. The process is straightforward and designed for indie developers who need quick access without bureaucratic delays.
Use Google or email registration
You can register using your Google account for instant access or opt for a traditional email and password combination. Note that Google sign-ups include a $0.50 free trial credit, while email accounts start with zero balance.
Key shown on dashboard immediately
Upon successful registration, your unique API key is displayed on the dashboard instantly. You can copy this key to use in your requests, and it remains visible for easy integration into your WordPress plugins or custom scripts.
- One active key per account
- New keys invalidate the old one immediately
- Visible on the dashboard for quick copying
First Request with cURL
Once you have your API key, you can start generating audio immediately using a simple cURL command. This method works for any developer environment and requires no additional libraries, making it a simple way to verify your integration is working correctly.
The endpoint accepts standard JSON payloads, allowing you to define the model, input text, voice selection, and audio format in a single request. You can test this locally before embedding it into your application logic.
POST to /v1/audio/speech
Send your request to https://api.play67bd.com/v1/audio/speech using the HTTP POST method. This endpoint handles the synthesis process and returns the generated audio file directly in the response body.
The API expects a JSON body containing the text to be spoken and the desired voice parameters. Ensure your text does not exceed 4096 characters per request.
- Endpoint:
https://api.play67bd.com/v1/audio/speech - Method:
POST - Content-Type:
application/json
Include Authorization header
Include your API key in the Authorization header using the Bearer token scheme. This authenticates your request and links the usage to your account balance.
Make sure to replace YOUR_API_KEY with the actual key provided on your dashboard. Each account has one active key at a time.
- Header:
Authorization: Bearer YOUR_API_KEY
Send JSON body with text and voice
The JSON body requires the model (e.g., tts-1), input (your text), and voice (e.g., nova). You can also specify response_format and speed.
Here is a complete example you can run in your terminal to generate a short audio clip.
- `curl -X POST https://api.play67bd.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"}'`

Using the OpenAI SDK
The ScribbleVoice API mirrors the OpenAI speech endpoint structure, allowing you to leverage familiar SDKs without learning a new protocol. By adjusting the base URL, your existing integration code works with minimal changes, making it ideal for indie developers who value simplicity.
We recommend using the official OpenAI SDKs for Python or Node.js. This approach reduces boilerplate and ensures compatibility with the standard request shape, letting you focus on your content rather than HTTP headers.
Change base_url to our API domain
Update your SDK configuration to point to https://api.play67bd.com/v1. This single change directs all requests to our infrastructure while maintaining the standard tts-1 or tts-1-hd model identifiers.
Use official OpenAI SDKs
The standard OpenAI libraries handle authentication and JSON serialization automatically. You can use your tts-... key as you would an OpenAI key, ensuring consistent behavior across different programming environments.
Same request shape as OpenAI
The JSON body expects model, input, voice, and response_format fields exactly as defined in the OpenAI specification. This consistency allows you to copy-paste examples directly from OpenAI documentation with only the base URL adjusted.
Supported Response Formats
Your API call returns raw audio bytes, allowing you to choose the format that best fits your workflow. Each format balances file size, compatibility, and quality differently, so select the one that matches your delivery needs.
All formats are generated from the same engine, ensuring consistent voice quality regardless of your choice. You can switch formats without reprocessing your text, keeping your integration flexible and efficient.
MP3 for web compatibility
MP3 is a widely supported audio format on the web. It offers a good balance between file size and quality, making it ideal for embedding audio players in WordPress blogs or sharing via social media links.
- Small file sizes for faster loading
WAV for high quality
WAV provides uncompressed audio. This format is perfect for professional editing, archiving, or scenarios where no data loss is acceptable.
- Lossless audio quality
- Ideal for post-production
Opus, FLAC, and PCM options
Opus offers high-quality compression at low bitrates, suitable for voice-heavy applications. FLAC provides lossless compression. PCM is raw, uncompressed audio data, best for direct processing pipelines.
Choose based on your storage constraints and playback requirements. All formats are available via the response_format parameter in your API request.
- Opus: Efficient compression
- FLAC: Lossless compression
- PCM: Raw audio data
Voice Selection and Languages
Choose from eight distinct voices tailored for different content types, from warm narration to energetic promos. Each voice is built on licensed recordings, ensuring consistent, high-quality synthetic speech for your blog or app without the need for complex infrastructure.
8 preset voices available
Select from four female voices (Aria, Nova, Luna, Sage) and four male voices (Felix, Milo, Atlas, Orion). These presets cover a range of tones, allowing you to match the voice to your specific content, whether it is a calm instructional guide or a bright, upbeat promotional clip.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Set language via ISO code
Explicitly define the language using its ISO code in the request. This ensures accurate pronunciation and intonation, especially when your text script might be ambiguous or when using non-English languages that share common scripts.
- Supported: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Auto-detection for Latin script
If the language parameter is omitted, the system guesses the language based on the script. Text in Latin script defaults to English. For non-English text using Latin characters, always set the language parameter to avoid incorrect pronunciation.

Rate Limits and Quotas
Each API key is limited to 60 requests per minute. This limit applies to all requests combined, so monitor your usage to avoid delays during peak integration testing.
60 requests per minute
After the initial period, your account supports 60 requests per minute. This allows generation for blogs and small apps.
10 requests per minute initially
New accounts start with a lower limit of 10 requests per minute. This helps stabilize the service while you test your integration.
Queue during high load
If many users are generating audio simultaneously, requests may queue. You will wait until processing is available. Long texts take longer to generate, so plan your batches accordingly.
Error Handling
When your request fails, the API returns a clear JSON error object. These errors are easy to parse and typically indicate a fixable issue with your request parameters or credentials, allowing you to retry confidently without wasting credits.
Invalid API key errors
If the API key is missing or incorrect, you will receive a 401 Unauthorized response. Ensure your Authorization header exactly matches the format Bearer tts-... as shown in your dashboard.
- Check for typos in the key string
- Ensure no extra spaces before or after the token
Input text too long errors
The API accepts up to 4096 characters per request. If your text exceeds this limit, you will receive a 400 Bad Request error. Split your text into smaller chunks and concatenate the resulting audio files.
- Count characters including spaces and punctuation
- Implement client-side splitting for long articles
Synthesis failure responses
Occasionally, synthesis may fail due to server-side issues. Failed requests are free. The API returns a specific error code to help you distinguish between retryable and non-retryable failures.
- Failed requests do not consume credits
- Check the error message for retry instructions

Authentication Details
Authentication is handled via the Authorization: Bearer <key> HTTP header. Your API key, issued upon sign-up, must be included in every request to https://api.play67bd.com/v1. This ensures your usage is correctly billed to your account balance.
Bearer token in Authorization header
Include your key exactly as shown on the dashboard. The format is Authorization: Bearer tts-.... Do not URL-encode the key unless your HTTP client requires it.
One active key per account
Each account holds a single active API key. You can generate a new key at any time from your dashboard. This simplifies key management for indie developers without needing complex rotation logic.
Revoke old key instantly on new issue
When you issue a new key, the previous one stops working immediately. There is no overlap period. Ensure your integration updates to the new key before the old one expires to avoid service interruption.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Publish your latest coding discoveries and personal reflections using a reliable blogging platform to grow your independent audience effectively.
23 languages
Any voice speaks any of these languages.
