Frequently asked questions
How do I get an API key?
Sign up on the /get-api-key/ page using Google or email plus password. The dashboard displays your active API key, balance, and usage stats. You can issue a new key at any time, which immediately invalidates the old one. Each account holds exactly one active key at a time.
What is the base URL for the API?
The API base URL is https://api.play35bd.com/v1. You send POST requests to https://api.play35bd.com/v1/audio/speech for synthesis. Other endpoints like /v1/voices and /v1/models are also available under this base URL structure for retrieving voice lists and model details.
Can I use the OpenAI SDK with this API?
Yes, the official OpenAI SDKs work perfectly. Simply change the base_url to https://api.play35bd.com/v1 and use your site-specific key. The request shape matches the OpenAI speech endpoint exactly, allowing you to integrate quickly without learning a new library or format.
What models are available?
Two models are available: tts-1 and tts-1-hd. Both use the same engine and pricing. You can choose between them based on your quality needs, but the cost per character remains identical regardless of which model you select for your synthesis requests.
What voices can I use?
Eight presets are available: aria, nova, luna, sage, felix, milo, atlas, and orion. Each voice supports all 23 listed languages. You can select any voice for any language, though setting the language parameter is recommended for non-English Latin script text to ensure accuracy.
How do I handle 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 audio for longer documents or scripts.
What response formats are supported?
You can choose from mp3, wav, opus, flac, and pcm. Specify the desired format using the response_format field in your JSON body. The API returns the audio file directly in the response, allowing you to save it immediately without additional conversion steps.
What are the rate limits?
You are limited to 60 requests per minute per key. Before your first top-up, this limit is 10 requests per minute. Requests are processed sequentially, so under load, you may experience queuing delays. Typical speed is roughly real time on long texts (about 25 characters per second).
How do I handle errors?
Failed requests are free, and the charge is returned in full if synthesis fails. You can monitor the status in your dashboard. If an error occurs, check your input format, voice availability, or rate limits. Support is by email only.
Is streaming supported?
No, streaming is not supported. The API returns the complete audio file after generation. There is no WebSocket or real-time partial audio delivery. You must wait for the full response before saving or playing the audio file locally.
Does the API support SSML?
No, SSML is not supported. You can only send plain text input. There are no phoneme dictionaries or custom pronunciation lexicons available. For precise control, you must manage text formatting in your application before sending it to the API endpoint.
How do I regenerate my API key?
You can issue a new key from your dashboard at any time. The old key stops working immediately when the new one is created. This ensures security if your key is compromised. You can issue a new key at any time from the account interface.
What happens if I exceed the rate limit?
Requests will be queued or rejected if you exceed the limit. The standard limit is 60 requests per minute, or 10 before your first top-up. Processing is sequential, so high volume may cause delays. Failed requests do not incur charges, protecting your balance.
Can I use multiple API keys?
No, each account has exactly one active key at a time. You can regenerate the key, but only one remains active. To use multiple keys, you would need separate accounts. The dashboard displays your current key, balance, and usage statistics.
First request
curl
curl https://api.play35bd.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.play35bd.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.play35bd.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
Get started by visiting the /get-api-key/ page to create your account. You can sign up quickly using your Google account or create a standard email and password login. This step initializes your account on the platform.
Once registered, you will receive a unique API key. This key is the only credential you need to authenticate your requests to the TTS engine and start generating audio files for your projects.
Sign up via Google or email
Creating an account takes only a few seconds. Using Google Sign-In is the fastest way to get your API key and immediate access to your dashboard, including trial credit. Alternatively, you can register with a simple email and password setup.
Your account is tied to the specific site you are using. Each site maintains its own independent user database, so a login on play35bd.com does not grant access to other domains in the network.
- Google Sign-In for instant setup
- Email and password option available
- Accounts are site-specific
One active key per account
Each account holds exactly one active API key at any given time. This single key authenticates all your requests. You will see this key displayed on your dashboard alongside your current balance and usage statistics.
The key format starts with 'tts-'. You must include it in the Authorization header of every request you send to the API endpoints.
Regenerate key if needed
If you suspect your key has been exposed or simply want a fresh start, you can regenerate your key at any time from the dashboard. This action is immediate.
When you issue a new key, the old one stops working instantly. There is no overlap period, so ensure you update your applications or scripts to use the new key before the old one becomes invalid.
First request with cURL
Send a POST request to https://api.play35bd.com/v1/audio/speech with your bearer token. The API accepts standard JSON payloads, allowing indie developers to integrate TTS using simple HTTP clients without complex setup.
POST to /v1/audio/speech
Direct your requests to the speech endpoint. Ensure your Authorization header includes Bearer tts-... with your active key. This single endpoint handles synthesis, returning the audio file or errors based on your input.
JSON body with model and input
Construct a JSON body including model (e.g., tts-1), input (your text, max 4096 characters), and voice (one of eight presets). You can also specify response_format, speed, and language. Keep it simple; the engine handles the rest.
- *
model: "tts-1" or "tts-1-hd" - *
input: String up to 4096 chars - *
voice: Preset like "nova" or "atlas" - *
response_format: mp3, wav, opus, flac, or pcm
Receive audio file in response
The response contains the generated audio file directly in the body. Save this binary data to a file on your server or device. For longer texts, split your input manually, process each chunk, and join the resulting audio files client-side.
Using the OpenAI SDK
You can use the official OpenAI SDKs directly by pointing them to our API. This means you don’t need to install a custom library or learn a new interface. The endpoint structure is identical to OpenAI’s, so your existing code likely works with minimal changes.
Change base_url to api.play35bd.com/v1
Update your SDK configuration to use our base URL instead of OpenAI’s. This redirects your requests to our infrastructure while keeping the same request shape.
Use official OpenAI SDKs
Any official OpenAI SDK (Python, Node.js, etc.) works out of the box. No custom client is needed because we mirror the standard endpoints exactly.
Replace your API key
Swap the standard OpenAI key with your Cloud TTS Indie key. Ensure your key starts with tts- to authenticate correctly against our endpoints.
Request parameters
The API accepts a model parameter to select the synthesis engine. You can choose between tts-1 for standard quality or tts-1-hd for higher fidelity. Both models use the same underlying engine and are priced identically, so your choice depends only on whether you prefer the specific audio characteristics of the HD version.
Model: tts-1 or tts-1-hd
Both tts-1 and tts-1-hd use the same engine and pricing. Use tts-1 or tts-1-hd based on your preference; they use the same engine. There is no performance difference in processing time or cost between the two options.
Voice: 8 presets available
Select one of eight voice presets to match your content’s tone. Each voice has a distinct character, from the warm narration of aria to the deep documentary style of orion. Any voice can speak any of the 23 supported languages, so set the language field explicitly if your text is in a non-English Latin script.
- Female: aria, nova, luna, sage
- Male: felix, milo, atlas, orion
- Voices are based on licensed recordings from LibriTTS-R
Speed: 0.25 to 4.0
Adjust the speed parameter between 0.25 and 4.0 to control the playback rate. The default speed is 1.0. Adjust this value to fit the pacing of your audio content. Adjust this value to fit the pacing of your audio content.
Response formats
You control the output format via the response_format field in your request. We support MP3, WAV, Opus, FLAC, and PCM. This flexibility lets you choose between smaller file sizes for web delivery or uncompressed quality for editing, without needing extra conversion steps.
MP3, WAV, Opus, FLAC, PCM
Each format serves a different workflow. Use MP3 or Opus for efficient bandwidth usage in apps. Choose WAV or FLAC if you need lossless audio for post-production. PCM is available for raw data processing. All formats are generated directly from the same engine, ensuring consistent voice quality across types.
- MP3: Compressed, ideal for web playback
- WAV: Uncompressed, standard for editing
- Opus: Highly efficient, small file size
- FLAC: Lossless compression, high fidelity
- PCM: Raw uncompressed audio data
Audio file returned directly
The API response contains the audio file directly in the body. You do not need to make a second call to download a file. The response includes appropriate headers so your client can save the file with the correct extension and type. This simplifies integration for indie developers who want a straightforward request-response cycle.
No streaming or WebSocket
We do not support streaming audio chunks or WebSocket connections. You receive the complete audio file only after synthesis finishes. For long texts, you must split the input into parts of up to 4096 characters and join the resulting files client-side. This synchronous approach keeps the integration simple and predictable.

Handling long texts
The API enforces a strict 4096-character limit per request. If your script or novel excerpt exceeds this, you must split the input text into smaller chunks before sending them to the endpoint. This ensures every part of your content gets processed without truncation errors.
Each chunk generates its own audio file. You can then concatenate these files in your preferred programming language to create a single, continuous audio track that matches the original narrative flow.
Split text into 4096 char parts
Break your input string at natural boundaries, such as sentence ends, to avoid cutting mid-word. Ensure each segment stays under the 4096 character limit, including spaces and punctuation.
The API does not handle splitting automatically, so this step must be implemented in your client code or middleware.
- Use sentence boundary detection for cleaner cuts.
- Count characters accurately, including spaces.
- Ensure no single chunk exceeds 4096 chars.
Generate audio for each part
Send each split chunk as a separate POST request to the /v1/audio/speech endpoint. The API processes these sequentially, so under load, you may experience slight delays between generations.
Each response contains a distinct audio file corresponding to that specific text segment.
- Maintain the same voice and speed settings for all chunks.
- Handle rate limits (60 req/min) between requests if needed.
- Store each audio file temporarily until processing is complete.
Join audio files client-side
Once all audio files are received, merge them using a library like ffmpeg or a language-specific audio package. This creates a continuous audio track, though gaps may occur depending on split points.
This approach works for any length of text, limited only by your storage and processing power.
- Use ffmpeg for reliable format merging.
- Ensure consistent sample rates across all files.
- Verify the final audio plays smoothly without abrupt cuts.
Rate limits
Your API key allows 60 requests per minute, which is plenty for most indie projects. Before your first top-up, you’re limited to 10 requests per minute. This lower limit helps manage initial load without requiring immediate payment.
If you hit the limit, your requests simply wait in a queue. They are processed one after another, so longer texts may take a bit longer to generate. Failed requests don’t count against your limit and are free.
60 requests per minute per key
Once you top up, you get 60 requests per minute. This is the standard limit for most indie developers and freelancers. You can monitor your usage directly on the dashboard.
- Limit resets every 60 seconds
- Applies per API key
- No hard cap on total characters
10 requests per minute before top-up
New accounts start with a 10 requests per minute limit. This is a gentle introduction to the service, allowing you to test the API with your free trial credit. Top up to unlock the full 60 req/min speed.
- Applies to all accounts without balance
- Unlocks automatically after top-up
- No need to wait for support
Requests processed in queue
Requests are processed sequentially. If you send many requests at once, they may wait in a queue. This ensures fair usage and prevents any single key from overwhelming the system. Short phrases might take a few seconds, while long texts take longer.
- Sequential processing
- No priority queue
- Fair usage policy
Common errors
Even with a straightforward API, you might hit a few common hurdles. Knowing these upfront saves you from debugging headaches when your indie project goes live. Here is what to watch for.
Most issues stem from authentication, input size, or temporary rate caps. The error messages are explicit, so you can fix them quickly without guessing.
Invalid API key
If the key is missing, malformed, or revoked, the API returns a 401 error. Ensure your Authorization header uses the correct Bearer token.
Regenerate your key via the dashboard if it was compromised. Note that revoking an old key stops it immediately.
- Check for typos in the Bearer token
- Verify the key matches your active account
- Regenerate via /get-api-key/ if needed
Input text too long
The API rejects inputs exceeding 4096 characters per request. If your script sends more, you will receive a 400 error.
Split your text into chunks of 4096 characters or fewer before sending each part.
Rate limit exceeded
New accounts are limited to 10 requests per minute. Once topped up, the limit increases to 60 requests per minute per key.
If you exceed the limit, requests queue up. Exceeding it significantly may result in a 429 error until the window resets.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- W3C WAI: making audio and video accessible
- openai-python on GitHub
- MDN: Web Speech API
- LibriTTS-R corpus (OpenSLR 141)
- curl documentation
- Tether (USDT)
- Creative Commons Attribution 4.0
- TRON developer hub: TRC-20
- LibriTTS-R paper (arXiv 2305.18802)
- OpenAI API reference: create speech
- openai-node on GitHub
