Frequently asked questions
How do I get an API key?
Sign up on the /get-api-key/ page using Google or email and password. Your account receives one active API key starting with 'tts-'. You can issue a new key at any time, which immediately invalidates the previous one.
What is the base URL?
The API base URL is https://api.good11.info/v1. Use this for all requests, including the speech endpoint and voice listing. The standard OpenAI SDK works by setting this as the base URL in your configuration.
Can I use the OpenAI SDK?
Yes. The API follows the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.good11.info/v1 and providing your site-specific API key.
How do I change the speed?
Include the 'speed' field in your JSON body, with a value between 0.25 and 4.0. This adjusts the playback rate of the generated audio.
What models are available?
Two models are available: 'tts-1' and 'tts-1-hd'. Both use the same engine and pricing. You can list available models via the GET /v1/models endpoint.
How do I handle long texts?
Split your text into parts of up to 4096 characters. Send each part as a separate request, then join the resulting audio files. Failed requests do not consume credit.
What happens if the API is slow?
Requests are processed sequentially, so under load a request may wait in a queue. Typical speed is roughly real-time for long texts, but short phrases take a few seconds. There is no SLA.
Is there a WebSocket endpoint?
No. There is no streaming, WebSocket, or real-time partial audio support. You send text and receive the complete audio file in the response.
Do I need to install an SDK?
No. You can use the official OpenAI SDK by adjusting the base URL, or use plain HTTP requests directly. There is no dedicated mobile SDK or WordPress plugin.
How do I verify my key?
Use the key in the Authorization header as 'Bearer tts-...'. The /get-api-key/ page displays your current key, balance, and usage stats. You can also list voices to confirm access.
What is the character limit?
Each request accepts up to 4096 characters in the 'input' field. Spaces and punctuation count toward this limit. For longer texts, split the input and join the audio files.
Can I use custom voices?
No. Custom voice cloning is not offered. You can choose from eight presets (e.g., aria, nova, felix) based on licensed recordings. Voices cannot be designed or uploaded by customers.
How do I handle errors?
If synthesis fails, the charge is returned in full. Check the response status code and message. Ensure your text is within the 4096-character limit and your key is valid.
Is there a rate limit?
Yes, 60 requests per minute per key. Before the first top-up, the limit is 10 requests per minute. Exceeding the limit may result in temporary rejection of requests.
First request
curl
curl https://api.good11.info/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.good11.info/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.good11.info/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
To authenticate your requests, include the Authorization header with your API key. Use the format Bearer tts-<your-key>. This key is generated when you sign up on the /get-api-key/ page.
Use Bearer token
Include the header Authorization: Bearer tts-<key> in every API call. This simple HTTP standard works with the official OpenAI SDKs by setting the base_url to https://api.good11.info/v1.
One key per account
Each account holds a single active API key. You can view it on your dashboard alongside your balance and usage stats.
Rotate keys as needed
You can issue a new key at any time. The old key stops working immediately, ensuring tight security if you suspect exposure.
Endpoints
The API exposes three primary endpoints for generating and managing speech. Use the POST endpoint to convert text into audio files, while the GET endpoints provide metadata about available voices and model configurations.
All requests are authenticated via Bearer token. The speech endpoint accepts JSON bodies matching the OpenAI standard, making integration straightforward for indie developers using existing SDKs.
POST /v1/audio/speech
Send text up to 4096 characters to receive an audio file. The body includes model, input, voice, response_format, and optional speed and language fields. Use tts-1 or tts-1-hd for the same engine.
- Endpoint: POST https://api.good11.info/v1/audio/speech
- Accepts: JSON body with text, voice, and format
GET /v1/voices
Retrieve the list of 8 voice presets (e.g., aria, nova, atlas) and supported languages. This endpoint confirms available formats and pricing details without generating audio.
- Endpoint: GET https://api.good11.info/v1/voices
- Returns: Voice IDs, languages, and supported formats
GET /v1/models
List available models. Currently, tts-1 and tts-1-hd are supported, offering identical synthesis quality and pricing.
- Endpoint: GET https://api.good11.info/v1/models
- Returns: Model IDs and versions
Request parameters
The API accepts standard parameters to control audio generation. You select a model, provide input text, and choose a voice preset. The request shape matches the OpenAI speech endpoint, allowing you to use existing SDKs with a simple base_url change.
Model: tts-1 or tts-1-hd
Choose between tts-1 or tts-1-hd; both use the same engine and quality. Both use the same underlying engine and price structure, so the decision depends on your quality needs rather than cost differences.
Input text up to 4096 chars
Send your script in the input field, limited to 4096 characters per request. For longer children's stories or educational materials, split the text into chunks, generate each part, and join the resulting audio files.
- Spaces and punctuation count toward the character limit.
- Requests are processed sequentially, so queueing may occur under load.
Voice presets like aria or nova
Select from eight licensed presets, such as aria for warm narration or nova for upbeat content. Each voice supports all 23 languages, though you should set the language parameter for non-English Latin text to ensure accuracy.
- aria: warm, clear narrator
- nova: bright, upbeat
- luna: soft, storytelling
- sage: calm, instructional
- felix: energetic, promo
- milo: friendly, conversational
Response formats
The API returns synthesized audio directly in the response body, supporting MP3, WAV, OPUS, FLAC, and PCM formats. This allows indie developers to seamlessly integrate audio files into children's stories or educational apps without additional conversion steps.
MP3, WAV, OPUS, FLAC, PCM
Choose the format that best fits your application's needs. MP3 and OPUS offer efficient compression for web delivery, while WAV and FLAC provide lossless quality. PCM is available for raw audio processing.
Audio file in response body
The generated audio file is returned immediately in the HTTP response body. There is no need to poll for completion or download from a separate URL. This approach simplifies integration for short phrases and longer texts split into parts.
No streaming or WebSocket
The API does not support streaming audio chunks or WebSocket connections. You receive the complete audio file upon request completion. This design ensures consistent delivery for discrete text inputs, suitable for most indie game and app scenarios.
Speed and language
Adjust playback speed between 0.25 and 4.0 to match your content’s pacing. Children’s stories often benefit from slower speeds for clarity, while educational materials may use faster rates for efficiency. This control allows precise alignment with your application’s user experience requirements without altering the voice character.
Speed from 0.25x to 4.0x
Set the speed parameter to modify audio duration. Values outside 0.25–4.0 are invalid. Adjusting speed does not affect character count billing; you pay for the input text length, not the resulting audio duration.
Optional ISO language code
Specify the language using its ISO code (e.g., "en", "de", "ja") to ensure correct pronunciation. All eight voices support all 23 listed languages. Explicitly setting the language prevents misinterpretation, especially for mixed-language texts or ambiguous scripts.
- Supported languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish.
Auto-detect if not set
If the language field is omitted, the API guesses the language from the text script. Latin script defaults to English. For non-English Latin text, always set the language parameter to avoid incorrect pronunciation. Detection is based on character sets, not semantic context.

Rate limits
The API enforces a strict limit of 60 requests per minute per active key. This cap applies uniformly regardless of text length or response format, ensuring fair resource distribution across all users.
60 requests per minute
Each API key allows up to 60 synthesis requests every minute. This limit resets continuously, allowing burst usage if the queue is empty. Monitor your usage dashboard to stay within bounds.
10 requests before top-up
New accounts without a top-up start with a lower limit of 10 requests per minute. This ensures that free trial users do not overwhelm the system before purchasing credits.
Queue under load
Requests are processed sequentially. Under heavy load, your request may wait in a queue before synthesis begins. Long texts take longer to generate, potentially affecting throughput. Plan your integration accordingly.
Error handling
When synthesis fails, the API returns a non-200 status code. The request is free, and any pre-paid balance is returned in full. This ensures you are not charged for incomplete audio files or server-side processing errors.
Failed requests are free
If the server cannot generate audio due to internal issues, the character count is not deducted from your balance. You can retry the request without penalty. This applies to transient errors during the processing queue.
Check status codes
Always inspect the HTTP response code. A 200 OK means the audio file is ready in the response body. Codes like 429 indicate you have hit the rate limit of 60 requests per minute.
Handle 4xx and 5xx errors
4xx errors usually mean invalid parameters, such as an unknown voice or text exceeding 4096 characters. 5xx errors indicate temporary server issues. Implement exponential backoff for retries to handle queue delays under load.
- 400: Invalid request body or parameters
- 401: Unauthorized or invalid API key
- 429: Rate limit exceeded
- 500: Internal server error
Code examples
Integrate FableTongue’s TTS API into your indie projects using standard HTTP requests or the OpenAI SDK. The endpoint accepts JSON payloads with your text, voice selection, and audio format preferences, returning the synthesized audio file directly in the response body.
cURL command example
Send a simple request using cURL to generate speech immediately. Replace YOUR_API_KEY with your secret key from the dashboard. This method works for any environment that supports HTTP POST requests.
- Specify the model (tts-1 or tts-1-hd).
- Set the voice (e.g., aria, nova).
- Choose the response format (mp3, wav, etc.).
OpenAI SDK integration
Use the official OpenAI SDKs by changing the base_url to https://api.good11.info/v1. Pass your FableTongue key as the Bearer token. This allows you to use familiar methods like client.audio.speech.create() without rewriting your integration logic.
- Initialize client with base_url and API key.
- Call the speech endpoint with standard parameters.
- Handle the returned audio file.
Python or JS snippets
For Python, use the requests library or the OpenAI client. In JavaScript, use fetch or the axios library. Ensure you handle the binary response data correctly to save the audio file locally or stream it to your application.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This foundation allows each preset to maintain consistent tonal integrity, whether delivering a soft bedtime narrative or an energetic children’s tale.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- openai-node on GitHub
- ISO 639 language codes
- TRON developer hub: TRC-20
- openai-python on GitHub
- LibriVox public-domain audiobooks
- Python documentation
- LibriTTS-R paper (arXiv 2305.18802)
- IETF RFC 7845: Ogg Opus
- W3C WAI: making audio and video accessible
- MDN: Web Speech API
- OpenAI API reference: create speech
