Frequently asked questions
How do I get an API key?
Sign up on the /get-api-key/ page using Google or an email and password. Accounts are specific to this site. Once registered, you receive one active key per account, which you can use immediately to start making requests to the API.
What is the base URL?
The API base URL is https://api.play7359.com/v1. You send POST requests to https://api.play7359.com/v1/audio/speech for synthesis. Other endpoints like /v1/voices and /v1/models are also available at this base path for retrieving configuration details.
Does it work with OpenAI SDK?
Yes. The request shape matches the OpenAI speech endpoint exactly. You can use the official OpenAI SDKs by changing the base_url to https://api.play7359.com/v1 and providing your site-specific key. This allows for easy integration without custom client code.
Which models are available?
Two models are available: tts-1 and tts-1-hd. Both use the same engine and pricing. You can list them via the GET /v1/models endpoint. Choose tts-1-hd or tts-1 depending on your specific needs, as they use the same engine and price.
How many characters per request?
Each request supports up to 4096 characters of input text. For longer texts, you must split them into chunks of this size and join the resulting audio files. Spaces and punctuation count toward this character limit.
What audio formats are supported?
You can choose from mp3, wav, opus, flac, and pcm. Specify the desired format in the response_format field of your request. The generated audio is returned directly in the response body for immediate use in your application.
What are the rate limits?
The limit is 60 requests per minute per key. Before your first top-up, this limit is reduced to 10 requests per minute. These limits apply to all API calls made with your active key within the specified time window.
What happens if I exceed limits?
If you exceed the rate limit, requests will be rejected. Failed requests are free, so you are not charged for audio generation that does not complete successfully. You must wait for the window to reset.
Can I change my API key?
Yes, you can issue a new key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. This allows you to rotate keys securely without downtime if needed.
How do I handle errors?
Check the HTTP status code and response body for error details. Failed synthesis requests return a full refund of the character cost. Monitor your response for status indicators to ensure your audio generation completed successfully before proceeding with your workflow.
Is there a webhook for status?
No, there is no webhook support. The API is synchronous; you send a request and receive the audio file or error in the immediate response. You do not need to poll for status or wait for asynchronous notifications.
Do I need to install a library?
No library is required. You can use plain HTTP requests or the official OpenAI SDKs. Since we do not provide an official SDK, using standard HTTP clients or the OpenAI library with a custom base_url is the recommended approach.
Can I use cURL only?
Yes, cURL is fully supported. A ready cURL example is provided on the /get-api-key/ page. You can send JSON bodies with model, input, voice, and other parameters directly via cURL to generate audio files efficiently from the command line.
How do I pass the language?
Pass the language as an optional ISO code in the request body. If omitted, the system guesses the language from the script, defaulting to English for Latin text. For non-English Latin-script text, always set the language explicitly for accuracy.
First request
curl
curl https://api.play7359.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.play7359.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.play7359.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 /get-api-key/ using Google or email to receive your API key instantly. Your dashboard displays the key, current balance, and usage stats. This single key authenticates all requests to the API endpoint.
Sign Up Process
Create an account via the /get-api-key/ page. Google sign-in grants a $0.50 trial credit valid for 7 days. Email-based accounts start with zero balance. No credit card is required to begin.
- Google or email registration
- Instant key generation
- Trial credit for Google users
Key Management
The dashboard shows your active key, remaining balance, and character count. Use this key in the Authorization header for all API calls. One active key per account ensures simple tracking.
Revoking Old Keys
Issue a new key from the dashboard anytime. The previous key stops working immediately. This allows instant revocation if a key is compromised or no longer needed.
First API Request
Once you have your API key, generating speech is a single HTTP POST request. The endpoint accepts standard JSON input, allowing you to specify the model, voice, and desired audio format. This straightforward structure ensures compatibility with existing developer workflows and tools.
The API returns the generated audio file directly in the response body, eliminating the need for polling or additional download steps. You can immediately play, store, or embed the audio in your blog posts or WordPress media library.
Curl Example
Use this cURL command to generate your first audio file. Replace YOUR_API_KEY with your secret key from the dashboard.
```bash curl -X POST https://api.play7359.com/v1/audio/speech \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "tts-1", "input": "Hello from BlogTTS", "voice": "nova", "response_format": "mp3"}' \ --output speech.mp3 ```
JSON Body Structure
The request body requires three mandatory fields: model, input, and voice. The input field accepts up to 4096 characters of text. Optional fields include response_format (defaulting to mp3), speed (0.25–4.0), and language.
The model field accepts either tts-1 or tts-1-hd. Both use the same engine and price. The voice field must match one of the eight available presets, such as nova or atlas.
Response Format
A successful request returns an HTTP 200 status with the audio binary data in the body. The content-type header matches your requested format (e.g., audio/mpeg for MP3).
If the request fails, the API returns an error JSON object with a code and message. Failed requests are free, and any charged amount is refunded automatically.
- HTTP 200 with audio binary data
- Standard error JSON on failure
- Automatic refund for failed synthesis
OpenAI SDK Integration
The official OpenAI SDKs work seamlessly with our API. You only need to change the base_url to https://api.play7359.com/v1 and provide your API key. This allows you to use familiar client libraries without rewriting your integration logic.
This approach keeps your codebase clean and leverages existing developer tools. You can switch between our TTS service and other OpenAI-compatible endpoints with minimal configuration changes, making it easy to prototype and scale your blog’s audio features.
Base URL Change
Update your SDK configuration to point to https://api.play7359.com/v1. This single change redirects all requests to our TTS endpoint while maintaining the standard request shape.
Ensure your Authorization header uses a key starting with tts-. The SDK handles the rest, sending your text and voice parameters exactly as defined in the OpenAI format.
SDK Compatibility
Any official OpenAI SDK (Python, Node.js, etc.) is compatible. Since our endpoint mirrors the OpenAI speech structure, you can use the same code patterns you already know.
This compatibility extends to other OpenAI-compatible clients as well. You do not need a proprietary SDK or library; standard HTTP libraries work just as effectively.
Code Snippets
- Set
base_urltohttps://api.play7359.com/v1in your SDK client initialization. - Pass
modelastts-1ortts-1-hd, along withinputandvoiceparameters. - Handle the binary audio response directly; no additional parsing is required for standard formats like MP3 or WAV.
Available Models
The API offers two model identifiers, tts-1 and tts-1-hd, which utilize the same underlying synthesis engine. This means the audio quality and voice characteristics remain consistent regardless of which model name you select in your requests, as both use the same engine.
tts-1 Model
Use tts-1 for standard generation. It processes text efficiently and is ideal for general blog content, podcast scripts, or standard voiceovers where speed is prioritized over studio-grade nuance.
tts-1-hd Model
The tts-1-hd identifier triggers the same engine but signals high-definition processing. It is suitable for content where audio clarity is critical, such as detailed tutorials or high-quality audiobooks.
Same Engine Price
Both models are billed at the same rate: $10 per 1 million characters. Since the engine is identical, you do not pay a premium for the "hd" label. Choose the model that fits your workflow without worrying about cost differences.
Supported Voices
The API provides eight distinct voice presets designed for diverse content styles. Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Every generated file includes an inaudible watermark identifying it as synthetic speech.
Female Voices
Four female options cover narrative, instructional, and energetic tones. Aria offers a warm, clear narrator style ideal for long-form blog posts. Nova provides a bright, upbeat voice for quick updates or promotional snippets. Luna delivers a soft, storytelling cadence suitable for serialized content, while Sage maintains a calm, instructional tone for tutorials.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
Male Voices
The male lineup includes four presets for news, conversation, and documentary styles. Felix brings energetic delivery perfect for promo content. Milo offers a friendly, conversational tone for personal blogs. Atlas provides a neutral, news-ready voice, and Orion delivers a deep, documentary-style narration for serious topics.
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Voice Selection
Select any voice for any of the 23 supported languages. While the API guesses language from the script (defaulting to English for Latin text), explicitly setting the language parameter ensures accuracy for non-English Latin-script content. All voices support the full range of languages, from Arabic to Turkish.

Audio Formats
The API returns audio in multiple formats to suit different workflows. MP3 is the default, offering a balance of quality and file size for web embedding. WAV provides uncompressed lossless audio, ideal for professional editing or archival purposes where bit-perfect fidelity is required.
MP3 Output
MP3 is the standard format for most use cases, providing efficient compression while maintaining clear speech quality. It is suitable for direct embedding in blog posts, podcasts, or web applications where bandwidth efficiency matters.
- Default response format
- Optimized for web embedding
- Balances quality and file size
WAV Output
WAV delivers uncompressed audio data, ensuring no loss in quality during generation. This format is preferred when you need to edit the audio further in software like Audacity or Premiere, or when storing high-fidelity voiceovers for future use.
- Lossless quality
- Ideal for post-production editing
- Larger file size than MP3
Other Formats
Beyond MP3 and WAV, you can request Opus, FLAC, or PCM. Opus offers high-quality compression for modern web standards. FLAC provides lossless compression, reducing file size without quality loss. PCM returns raw audio data, useful for specific hardware integrations or precise sample-level manipulation.
- Opus: Modern web standard
- FLAC: Lossless compression
- PCM: Raw audio data
Rate Limits
Rate limits ensure fair usage of our synthesis infrastructure. Understanding these constraints helps you plan your content pipeline without unexpected interruptions during peak writing hours.
Our limits are straightforward: a standard cap of 60 requests per minute per key, with a lower threshold for new accounts before their first top-up.
60 Requests Per Minute
After your account is established and funded, you can send up to 60 requests per minute. This allows for rapid generation of multiple audio files for blog posts or newsletters.
Since requests are processed sequentially, high-volume batches may queue briefly. Typical generation speed is roughly real-time, meaning 25 characters of text per second of audio.
- Standard limit: 60 requests/minute/key
- Processing is sequential under load
- Long texts split into 4096-char parts
10 Requests Before Top-Up
New accounts start with a lower limit of 10 requests per minute. This applies until you complete your first top-up via USDT on the TRON network.
Once the transfer is credited, your limit increases to the standard 60 requests per minute immediately.
Limit Handling
Monitor your usage dashboard to track remaining capacity. If you hit the limit, wait a minute or implement a retry loop with exponential backoff in your code.
Failed requests are refunded, but the rate limit applies to requests sent. You can safely retry without penalty if a temporary network issue occurs.
Error Handling
The API returns standard HTTP status codes to indicate success or failure. A 200 OK response confirms synthesis completion, while 4xx errors indicate client-side issues like invalid keys or malformed JSON. 5xx errors suggest temporary server-side problems, often due to queue congestion during high load.
Common Error Codes
Use 401 Unauthorized for invalid or expired API keys. 429 Too Many Requests appears when you exceed 60 requests per minute. 400 Bad Request indicates missing fields or text exceeding 4096 characters.
- 401: Invalid key
- 429: Rate limit exceeded
- 400: Malformed JSON
Failed Request Refund
If synthesis fails due to server errors or timeouts, the charge is returned in full. You are not billed for failed requests. Check your dashboard balance to confirm refunds appear automatically within minutes.
Debugging Tips
Verify your key format starts with 'tts-'. Ensure text input is under 4096 characters. Check that your model and voice parameters match the /v1/voices endpoint list. Enable verbose logging to capture full response headers for support tickets.
- Check key prefix
- Limit text length
- Verify voice IDs
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The limit resets every minute, so you can plan your generation bursts around peak publishing times.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- openai-python on GitHub
- openai-node on GitHub
- LibriVox public-domain audiobooks
- TRON developer hub: TRC-20
- ISO 639 language codes
- W3C WAI: making audio and video accessible
- IETF RFC 7845: Ogg Opus
- OpenAI API reference: create speech
- Python documentation
- LibriTTS-R paper (arXiv 2305.18802)
- curl documentation
