Frequently asked questions
What is a text-to-speech API?
A cloud service that converts text into audio files via a simple HTTP request. You send text to our endpoint and receive an audio file in formats like MP3 or WAV. It works like the OpenAI speech endpoint, allowing you to use standard SDKs by adjusting the base URL for easy integration into your applications.
How do I read aloud Bible stories programmatically?
Send a POST request to https://api.good11.info/v1/audio/speech with your text and desired voice. For longer stories, split the text into chunks under 4096 characters, generate each audio file, and join them. Use the tts-1 model for standard quality or tts-1-hd for higher fidelity, ensuring your app handles the resulting audio files seamlessly.
Which voices are best for children's stories?
Aria offers a warm, clear narrator style, while Luna provides a soft, storytelling tone suitable for gentle narratives. Nova is bright and upbeat for energetic tales, and Sage delivers a calm, instructional voice for educational content. Each voice supports all 23 languages, allowing you to maintain consistency across different regional versions of your stories.
Can I use the API for commercial apps?
Yes, the API is designed for integration into applications, including commercial ones. You pay based on usage at $10 per million characters, with no monthly plans or minimum spend. Generated audio is returned in the response and not stored, ensuring your data usage remains private and compliant with your application’s specific requirements.
How long is the free trial?
The free trial provides $0.50 of credit, equivalent to approximately 50,000 characters. This credit is valid for 7 days and is granted when you sign in with Google. Accounts created with email and password start without this trial credit, allowing you to test the API’s quality before committing to USDT payments.
What languages are supported?
We support 23 languages including English, Spanish, French, German, Japanese, Korean, and Arabic. Any voice can speak any of these languages. If you do not set the language parameter, it is guessed from the script, so you should explicitly set it for non-English Latin-script text to ensure accurate pronunciation and delivery.
Do I need to split long texts into parts?
Yes, each request supports up to 4096 characters. For longer texts, you must split them into parts, send each part to the API, and join the resulting audio files. This ensures reliable processing, as requests are handled sequentially and longer inputs might exceed the single-request character limit defined by our endpoint specifications.
Is there a limit on requests per minute?
You are limited to 60 requests per minute per API key. Before your first top-up, this limit is reduced to 10 requests per minute. This rate limit helps manage server load during peak times, so you should implement retry logic with exponential backoff in your application to handle any temporary throttling gracefully.
How does the USDT payment work?
We accept USDT on the TRON network (TRC-20) with a minimum top-up of $5. Payments are credited automatically within minutes after the transfer is confirmed on the blockchain. There are no subscriptions, invoices, or VAT charges, and your balance does not expire, providing a straightforward and transparent payment method for your usage needs.
Are there any hidden fees?
No, the price is strictly $10 per million characters, with spaces and punctuation counting as characters. Failed requests are free, and any charges for them are returned in full. There are no monthly plans, seats, or minimum spend requirements, ensuring you only pay for the exact volume of text you process successfully.
Can I change my API key?
Yes, you can issue a new API key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. This allows you to revoke access instantly if a key is compromised or if you need to rotate credentials for different environments within your application.
What happens if a request fails?
If synthesis fails, the charge is returned in full, so you are not billed for unsuccessful attempts. Failed requests do not consume your character limit or balance. You should check the response status code to determine if you need to retry the request or adjust parameters like voice or text length.
Is the audio watermarked?
Yes, every generated audio file carries an inaudible watermark that marks it as synthetic speech. This helps identify the content as AI-generated without affecting the listening experience. The watermark is embedded in the audio data itself, ensuring that the origin of the speech can be verified if needed for your applications.
How do I contact support?
Support is available via email only. We do not offer phone support, live chat, or SLAs. You can reach us through the contact page on our site. Since we are an independent storefront, responses are handled by our team directly, ensuring you get specific assistance regarding your API usage or billing questions.
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.mp3How it works for your app
Integrate high-quality narration into your Bible story app with a straightforward API. Send your script as text, and receive a synthesized audio file ready for playback. This simple workflow allows indie developers to add accessible audio content without managing complex infrastructure.
Send text, receive audio
Post a JSON payload to the speech endpoint with your text and desired voice settings. The system processes the request and returns the audio file directly in the response, ready to be played in your application.
Support for 23 languages
Tell stories in multiple languages using the same engine. Whether your audience reads English, Spanish, or Arabic, our API supports 23 languages including Hebrew, Hindi, and German. You can specify the language explicitly or let the system guess from the script.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Easy integration with OpenAI SDKs
If you already use the OpenAI SDK, you can switch to our API by simply changing the base URL. This allows you to keep your existing code structure while benefiting from our specific voice presets and pricing.
Voices for your content
Select from eight distinct voice presets to match the tone of your digital Bible stories or educational materials. Every voice is generated from licensed recordings, ensuring consistent quality and an inaudible synthetic watermark in every file.
Aria: warm, clear narrator
Aria delivers a clear, warm narration style ideal for reading parables or instructional content. Her tone remains steady and easy to follow, making her suitable for both children's stories and educational texts.
- Best for: Narratives and clear instructional text
Nova: bright, upbeat
Nova offers a bright, energetic delivery that keeps listeners engaged. This preset works well for dynamic storytelling or promotional app features where a lively tone is preferred.
- Best for: Engaging, lively content
Luna: soft, storytelling
Luna provides a soft, soothing voice perfect for bedtime Bible stories or calming educational materials. Her gentle pacing helps create a relaxing listening experience for users.
- Best for: Calm, narrative content
Technical specifications
The API returns audio in MP3, WAV, OPUS, FLAC, or PCM formats. These options cover most indie development needs, from web playback to high-fidelity archival.
MP3, WAV, OPUS, FLAC, PCM formats
Choose the format that best fits your application’s constraints. MP3 offers small file sizes for web delivery, while WAV and FLAC provide lossless quality for educational materials. PCM is available for raw audio processing.
Speed control from 0.25x to 4.0x
Adjust playback speed between 0.25x and 4.0x to match your audience. Slower speeds aid comprehension for children's stories, while faster speeds help users consume longer educational texts efficiently.
Character limit of 4096 per request
Each request accepts up to 4,096 characters. For longer texts, split the input into parts and join the resulting audio files. This ensures consistent quality and manageable processing times.
Pricing and costs
The TTS API charges $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. Failed requests are free, ensuring you only pay for successful audio generation. This straightforward model suits indie developers building Bible story apps without complex billing structures.
There are no monthly plans, seats, or minimum spend requirements. You can top up as needed, and your balance never expires. This transparency helps you predict costs accurately while developing educational reading tools or audiobook generation features.
$0.01 per 1,000 characters
Each request processes up to 4,096 characters. Longer texts are split and joined automatically. You receive audio files directly, with no per-minute or per-voice fees added to the base character rate.
- Spaces and punctuation count as characters
- Failed requests are fully refunded
- Long texts split into 4,096-character parts
No hidden fees or subscriptions
Unlike many platforms, we do not charge for seat management or subscription tiers. The API key is the only requirement for access. You can issue a new key anytime, with the old one stopping immediately.
Pay with USDT on TRON network
We accept USDT on the TRON network (TRC-20) for top-ups. The minimum deposit is $5, and credits are added automatically within minutes. We do not process credit cards, PayPal, or invoices with VAT.
- USDT on TRON (TRC-20)
- Minimum $5 top-up
- No cards or PayPal
Accessibility features
Every audio file generated by our API includes an inaudible digital watermark that clearly marks the content as synthetic speech. This ensures transparency for end-users and helps maintain trust in your Bible story or educational applications without requiring visual cues.
The engine delivers consistent audio quality across all 23 supported languages. Whether you are generating short verses or longer narratives, the voice remains stable, ensuring a professional listening experience for your users.
Synthetic speech watermark
The watermark is embedded directly into the audio stream. It is inaudible to human ears but can be detected programmatically if needed.
Consistent audio quality
Quality does not fluctuate based on text length or language. We use the same high-quality engine for all requests, ensuring your app feels reliable.
Failed requests are refunded, so you never pay for inconsistent or broken audio outputs.
- Inaudible to human listeners
Support for multiple scripts
Our API handles Latin, Cyrillic, Arabic, Hebrew, Chinese, Japanese, and Korean scripts natively. The system automatically detects the script to select the appropriate voice.
For non-English Latin text, we recommend setting the language parameter explicitly to ensure accurate pronunciation.
- Latin script

Use cases for indie devs
Transform static text into engaging audio experiences for your indie projects. Our API allows you to convert scripture, lessons, or stories into high-quality speech files with minimal code. Indie developers can integrate TTS directly into apps for children’s stories or educational materials without managing complex voice infrastructure.
By leveraging our straightforward API, you can deliver consistent audio output across 23 languages. This ensures your digital content remains accessible to diverse audiences, from young listeners to language learners, using a single reliable endpoint.
Digital Bible story apps
Integrate warm narration like Aria or Luna to bring biblical narratives to life. You can send short verses or longer parables up to 4096 characters per request. The API returns audio files instantly, allowing your app to stream or cache content for offline use.
- Support for 23 languages including English, Spanish, and Arabic
- Fast generation suitable for interactive app experiences
- No need for external voice actors or recording studios
Educational reading tools
Provide auditory support for literacy programs or language learning. Use voices like Sage for instructional clarity or Felix for energetic engagement. Developers can adjust speed from 0.25x to 4.0x to match the learner's pace, ensuring the audio remains clear and digestible.
- Adjustable speed for different reading levels
- Clear articulation ideal for vocabulary practice
- Works with standard OpenAI SDKs for easy integration
Audiobook generation
Convert public domain texts or user-generated content into audiobooks efficiently. Split longer manuscripts into 4096-character chunks and join the resulting audio files. With fair pricing at $0.01 per 1,000 characters, you can scale your library without high upfront costs.
- Cost-effective for large volumes of text
- Automatic character splitting handled by your logic
- Multiple format support (MP3, WAV, OPUS) for various players
Getting started
Start by creating an account on /get-api-key/ using Google or email. New accounts receive a $0.50 trial credit, valid for seven days, allowing you to generate approximately 50,000 characters of speech without payment details.
Sign up for a free trial
Visit /get-api-key/ and choose your preferred login method. The trial activates immediately, giving you immediate access to test the API’s capabilities with real text-to-speech generation.
Get your API key
Once registered, your dashboard displays your unique API key and current balance. You can issue a new key at any time, which instantly invalidates the previous one for security.
- Use the key in the
Authorization: Bearerheader.
Follow our quickstart guide
Use the official OpenAI SDKs by pointing base_url to https://api.good11.info/v1. Send a POST request to /v1/audio/speech with your text and desired voice preset. See /docs/ for full code examples.
Why choose Good11?
Good11 offers a straightforward pricing model with no hidden fees or subscriptions. You pay only for what you use, with clear costs per character.
Our API integrates easily with existing tools, allowing indie developers to add text-to-speech functionality quickly and efficiently.
Transparent pricing
We charge $0.01 per 1,000 characters, making it easy to predict costs. Failed requests are free, ensuring you only pay for successful audio generation.
- $0.01 per 1,000 characters
- Free failed requests
- No hidden fees
No monthly plans
Unlike many competitors, we do not require monthly plans or minimum spend. Our balance does not expire, giving you flexibility in how you manage your usage.
- No monthly plans
- No minimum spend
- Balance does not expire
Simple technical setup
Our API follows the OpenAI request shape, so you can use the official OpenAI SDKs with a simple base_url change. This makes integration quick and straightforward for indie developers.
- OpenAI SDK compatible
- Simple base_url change
- Quick integration
Data and privacy
Your input text is used solely to generate the requested audio file and is never used to train our models. This ensures that your story content remains private and distinct from our training data.
The generated audio is returned directly in the API response and is not stored on our servers. Once you receive the file, we have no copy of it, ensuring minimal data retention for your digital Bible stories or educational apps.
Text not used for training ['We use your input text exclusively for the immediate production of audio. It is not added to any training datasets, preserving the uniqueness of your narratives.']
Audio not stored after generation ['Audio files are delivered in the response and are not kept on our servers. This minimizes storage risks and ensures you retain full control over your generated content.']
Metadata kept for billing only ['We retain request metadata, including timestamp, character count, and status, strictly for billing and usage tracking. This data helps us process your USDT payments accurately and monitor your 60 requests per minute limit.']
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
- TRON developer hub: TRC-20
- Tether (USDT)
- OpenAI API reference: create speech
- LibriTTS-R paper (arXiv 2305.18802)
- W3C WAI: making audio and video accessible
- openai-python on GitHub
- Creative Commons Attribution 4.0
- ISO 639 language codes
- Node.js documentation
- Python documentation
- LibriVox public-domain audiobooks
