Frequently asked questions
How do I generate an API key?
Navigate to the /get-api-key/ page on combowin.top and sign up using Google or an email and password combination. The dashboard will display your unique API key, current balance, and usage statistics. You can also generate a new key at any time, which immediately invalidates the previous one.
Can I use the OpenAI Python SDK?
Yes, the API uses the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.combowin.top/v1 and providing your site-specific key. This allows you to integrate TTS generation into your existing Python workflows seamlessly.
What is the max characters per request?
Each request supports a maximum of 4096 characters in the input field. This limit applies to the text payload sent to the POST endpoint. For longer scripts, you should split your text into chunks of up to 4096 characters and join the resulting audio files.
How do I set the language explicitly?
Include the optional 'language' field in your JSON body with the ISO code for your target language. If omitted, the system guesses the language based on the script, defaulting to English for Latin text. Explicitly setting it ensures accurate pronunciation for non-English Latin-script texts.
Does the API support streaming audio?
No, the API does not support streaming, WebSocket connections, or real-time partial audio. It returns the complete audio file upon request completion. You receive the full audio data only after the synthesis process finishes, which typically takes a few seconds for short phrases.
What happens if the server is busy?
Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real time, but short phrases take a few seconds. Failed requests are free, and the charge is returned in full if synthesis fails due to server issues.
Can I use the same key on different sites?
No, accounts are per site. Each site in the network is an independent storefront, meaning your API key is specific to combowin.top. You would need to sign up separately on other sites to obtain distinct keys for those environments.
How do I cancel my API key?
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 effectively cancels the previous key without needing to contact support or wait for a processing period.
Is SSML supported for pronunciation?
No, the API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You cannot use SSML tags to control pacing or pronunciation. You must rely on the standard text input and the eight available voice presets for your audio generation needs.
Do I need to split long texts manually?
Yes, you must split texts longer than 4096 characters into parts yourself. The API processes each request independently. You should split your script into chunks, generate audio for each, and then join the resulting audio files to create your final lesson or module.
What is the speed range parameter?
The speed parameter accepts values between 0.25 and 4.0. This allows you to adjust the playback rate of the generated audio. You can slow down narration for clarity or speed up content for quick reviews, depending on your instructional design requirements.
Can I get raw PCM data?
Yes, you can request raw PCM data by setting the response_format parameter to 'pcm'. Other available formats include mp3, wav, opus, and flac.
How do I handle audio file sizes?
Audio generation takes roughly real time, about 25 characters per second. File sizes depend on the format and speed selected. PCM files will be larger than compressed formats like mp3 or opus. Plan your storage accordingly, as generated audio is returned in the response and not stored.
Is the API key secure for frontend use?
The documentation does not specify frontend security constraints, but each account has one active key. Since you can revoke and regenerate keys instantly, you can mitigate risks by generating a temporary key for frontend use and revoking it afterward. Rate limits apply per key.
First request
curl
curl https://api.combowin.top/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.combowin.top/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.combowin.top/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 and API key
To start using AudioTeach for your course narration, first generate an API key on the /get-api-key/ page. You can sign up using Google or an email and password. This key is essential for authenticating your requests to the API.
Once you have your key, include it in the Authorization header of every request. Use the format Bearer tts-your_key_here. This simple step ensures your API calls are recognized and processed correctly by our servers.
Generate key on /get-api-key/
Visit the /get-api-key/ page to create your account. You can sign in with Google or use a standard email and password combination. The page will display your unique API key, current balance, and usage statistics.
Your key allows you to generate audio files for your online modules. Keep this key secure, as it is the only credential needed to access your account's resources.
- Sign up with Google or email/password
- View key, balance, and usage stats
- Copy key for API requests
Bearer token in Authorization header
Include your API key in the Authorization header of each HTTP request. Use the Bearer scheme followed by your key. This header authenticates your requests and ensures you are billed to the correct account.
Example: Authorization: Bearer tts-1234567890abcdef. This format is compatible with most HTTP clients and SDKs, making integration straightforward for educators and developers alike.
- Use
Authorization: Bearer <your_key> - Include in every request header
- Compatible with standard HTTP clients
One key per account, replaceable
Each account has one active API key. If you need to revoke access or rotate your key, you can issue a new one at any time. The old key will stop working immediately.
This feature allows you to manage access securely. For example, if a team member leaves or a key is exposed, you can generate a new key without affecting your account balance or settings.
- One active key per account
- Generate new key anytime
- Old key stops immediately
Endpoint structure
The API exposes three primary endpoints for generating and managing speech assets. Use POST /v1/audio/speech to convert your script text into audio files. For asset discovery, GET /v1/voices lists available presets, languages, and formats, while GET /v1/models provides engine details.
These endpoints allow you to build lightweight integration with your LMS or course authoring tool. You can fetch the voice catalog to map specific characters to the correct preset, ensuring consistent narration across different modules without manual file management.
POST /v1/audio/speech
Send your script text here to generate audio. This is the core endpoint for creating voice lines, game show host intros, or narrator commentary. You provide the text, select a voice, and receive the audio file directly in the response.
- Endpoint:
POST https://api.combowin.top/v1/audio/speech - Accepts JSON body with
model,input,voice, and optional parameters. - Returns the audio file in the specified format.
GET /v1/voices for list
Retrieve the full list of available voices, their supported languages, and compatible audio formats. This helps you quickly identify which preset fits your character, whether you need the bright tone of Nova for upbeat quizzes or the calm instruction of Sage for explanations.
- Endpoint:
GET https://api.combowin.top/v1/voices - Returns voice ID, name, gender, and supported languages.
- Use this to build a dynamic voice selector in your authoring tool.
GET /v1/models for details
Check the available models (tts-1 and tts-1-hd) and their technical specifications. This endpoint confirms that both models use the same engine and pricing, allowing you to switch between standard and high-definition quality based on your project's needs without changing your code structure.
- Endpoint:
GET https://api.combowin.top/v1/models - Lists model ID, name, and engine details.
- Confirms pricing parity between
tts-1andtts-1-hd.
Request parameters
The request body requires three core fields to generate audio. You must specify the model, provide the text content, and select a voice preset. Each request handles up to 4096 characters of input text, which includes spaces and punctuation. For longer game show scripts, split the text into chunks and join the resulting audio files later.
All generated audio files carry an inaudible watermark marking them as synthetic speech. This applies to every format and voice combination. The API processes requests sequentially, so under load, synthesis may queue. Typical generation speed is roughly real-time, averaging about 25 characters of text per second of audio output.
subs: [{
Response formats
The API returns the raw audio file directly in the response body. The format is determined by the response_format parameter in your request, allowing you to choose between mp3, wav, opus, flac, or pcm based on your LMS compatibility needs.
mp3, wav, opus, flac, pcm
Select the format that best fits your course player. MP3 offers efficient compression for web delivery, while WAV and FLAC provide high-fidelity audio for archival or high-quality module hosting. PCM is available for uncompressed, raw audio processing.
Binary audio file in response
The response body contains the binary audio data itself. There is no intermediate wrapper or envelope; the file stream is immediate upon successful synthesis. This simplifies integration, as you can pipe the response directly to a file or audio element.
JSON metadata for status
The API returns the raw audio file directly. Request metadata (time, characters, status) is kept for billing, but the response itself contains only the audio data.
Rate limits and quotas
Rate limits protect the API during peak usage. Your key allows 60 requests per minute once active. This ensures fair access for all educators generating voice lines for their online modules.
Before your first top-up, you are limited to 10 requests per minute. This lower limit helps manage initial load while you test the integration with your LMS or course platform.
60 requests per minute
Once your account is funded, you can make up to 60 requests per minute. This is sufficient for generating most game show narration or character dialogues without hitting the cap immediately.
- Standard limit for active accounts
10 requests before first top-up
New accounts start with a 10 requests per minute limit. This allows you to verify the API works with your specific use case before committing to a USDT top-up.
Queue processing under load
Requests are processed sequentially. If you exceed the limit or during high traffic, your request may wait in a queue. Longer texts take more time to synthesize, so plan your generation batches accordingly.

Error handling and codes
When your API key is missing, expired, or incorrect, the server returns a 401 error. This ensures your game show voice lines aren’t generated by unauthorized requests. Check your key in the dashboard or regenerate it if needed.
Rate limits protect the service during peak usage in course production. If you exceed 60 requests per minute, you’ll receive a 429 error. New accounts start with a 10-request-per-minute limit until the first top-up.
401 for invalid key
Ensure your Authorization header includes the correct Bearer token. If you issued a new key, the old one stops immediately.
You can regenerate your key at any time from your dashboard.
- Check for typos in the token
- Verify no extra spaces in the header
429 for rate limit
The limit is 60 requests per minute per key. Under load, requests may queue, causing delays.
New accounts start with 10 requests per minute.
- Implement retry logic with exponential backoff
- Monitor usage in the dashboard
500 for synthesis failure
If synthesis fails, the charge is returned in full. This ensures you don’t pay for lost audio.
Check your input text for length limits (4096 characters).
- Verify text length
- Check voice and format compatibility
OpenAI SDK compatibility
The API mirrors the OpenAI speech endpoint structure, allowing you to reuse existing integration code with minimal adjustments. This compatibility is ideal for instructional designers already familiar with OpenAI’s client libraries, enabling rapid prototyping of voice lines for your online courses without learning a new SDK from scratch.
You only need to redirect the client’s base URL to our domain. The request shape, parameters, and response format remain identical to the standard OpenAI speech endpoint, ensuring a smooth transition for your development workflow.
Use official OpenAI SDK
Leverage the official OpenAI Python or JavaScript SDKs directly. Since our endpoint follows the same JSON schema, you can import the standard openai package and configure it to point to our infrastructure.
Change base_url to api domain
Configure your SDK client to use https://api.combowin.top/v1 as the base URL. This simple configuration change routes all speech requests to our servers while keeping your existing authentication and code structure intact.
Ensure your API key is passed via the Authorization: Bearer header as usual.
Standard speech method
Call the standard client.audio.speech.create() method with your parameters. Pass the model, input, voice, and response_format just as you would for OpenAI. The response returns a binary audio file.
cURL example for first request
Use cURL to test your integration quickly. Replace YOUR_API_KEY with your actual key from the dashboard.
This command sends a short text string to the API and saves the resulting audio file to your local drive.
Basic POST request structure
Send a POST request to the speech endpoint. Include the JSON body with your text and voice selection. The API returns binary audio data directly.
Required headers and body
Set the Authorization header with your Bearer token. The body must include the model, input text, voice preset, and desired response format. Ensure the text length stays within 4096 characters.
Example with Felix voice
Use the Felix voice for energetic promo lines. Replace the placeholder key and adjust the text as needed for your specific game show segment.
This example generates an MP3 file named promo.mp3. Adjust the --output flag if you prefer WAV or OPUS formats for your LMS.
https://api.combowin.top/v1/audio/speechtts-1felixmp3
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Technical terms and specific instructions are articulated with precision.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- Creative Commons Attribution 4.0
- openai-node on GitHub
- LibriTTS-R paper (arXiv 2305.18802)
- LibriTTS-R corpus (OpenSLR 141)
- Python documentation
- OpenAI API reference: create speech
- Tether (USDT)
- LibriVox public-domain audiobooks
- IETF RFC 7845: Ogg Opus
- W3C WAI: making audio and video accessible
- openai-python on GitHub
