Frequently asked questions
Is this site affiliated with OpenAI?
No. We are an independent storefront for our own text-to-speech API. While our endpoint shape matches the OpenAI speech endpoint for easy SDK integration, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons.
Who owns the voices?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated file carries an inaudible watermark marking it as synthetic speech. We do not offer custom voice cloning or voice design.
Do you store my text?
No. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata (time, characters, status) strictly for billing purposes.
How do I contact you?
Support is by email only. We do not have a phone number, live chat, or on-call support team. You can reach us via the contact page. We aim to respond to your inquiries as quickly as possible.
Is there a phone number?
No. We do not offer phone support. All customer support is handled via email. This allows us to keep our operations lean and focused on providing a reliable, cost-effective API for self-publishers and audiobook creators.
Do you have an SLA?
No. We do not offer an SLA, uptime guarantee, or enterprise contract. Requests are processed one after another, so under load a request may wait in a queue. Typical speed is roughly real time on long texts.
Are you certified?
No. We do not hold certifications such as SOC 2, HIPAA, or GDPR certificates. We are an independent provider focused on delivering natural-sounding narration in 23 languages without the overhead of enterprise-grade compliance certifications.
What is the base URL?
The API base URL is https://api.44bd.info/v1. You can use the official OpenAI SDKs by changing the base_url to this address and using your site's key. The endpoint for speech is POST /v1/audio/speech.
Do you offer refunds?
Yes, automatically. Failed requests are free: if synthesis fails, the charge is returned in full. Your balance does not expire, and you can top up with USDT on the TRON network. No invoices or VAT are involved.
Can I use the audio commercially?
Yes. The voices are based on CC BY 4.0 and public-domain sources. You can generate natural-sounding narration for your audiobooks and sell them. Each file includes an inaudible watermark to identify it as synthetic speech.
Is the API reliable?
Requests are processed sequentially. Under load, a request may wait in a queue. Typical speed is roughly real time (25 characters per second). Short phrases take a few seconds. We do not guarantee uptime or reliability.
Do you have a mobile app?
No. We do not have a mobile SDK or app. You can access our API from any device using the OpenAI SDK or plain HTTP. Our interface is web-based, designed for developers and no-code users.
Do you have a WordPress plugin?
No. We do not offer a WordPress plugin, browser extension, or official SDK of our own. You can integrate our API into your WordPress site using standard HTTP requests or the OpenAI Python/Node SDKs.
Do you offer custom voices?
No. We do not offer custom voice cloning for customers, nor do you upload your own voice. We provide eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) based on licensed recordings.
Do you offer emotion tags?
No. Our API does not support emotion tags, SSML, or phoneme dictionaries. You control tone by selecting specific voices like Aria for warm narration or Felix for energetic promos. Custom pronunciation is not available.
Do you offer phoneme dictionaries?
No. We do not provide phoneme dictionaries or custom pronunciation lexicons. The language is guessed from the script or set via the optional language parameter. You cannot fine-tune individual word pronunciations in the generated audio.
Do you offer speech-to-text?
No. We are a text-to-speech API only. We do not offer speech-to-text, translation, dubbing pipelines, or video editing. Our focus is solely on converting your text manuscripts into listenable audio files.
Do you offer translation?
No. We do not offer translation services. You must provide the text in one of our 23 supported languages. The API generates audio from the text you submit, without translating it for you.
Do you offer dubbing?
No. We do not offer a dubbing pipeline. We generate audio from text. You can use our API to create narration for your projects, but we do not handle video synchronization or dubbing workflows.
Do you offer video editing?
No. We do not offer video editing tools. We provide a text-to-speech API that returns audio files. You can use these audio files in your video editing software, but we do not edit the video itself.
Who We Are
TextReader Hub is an independent storefront for a text-to-speech API, designed to help self-publishers and audiobook creators turn manuscripts into listenable audio. We focus on simplicity, allowing you to generate natural-sounding narration in 23 languages without hiring voice actors.
Independent Team
We are a small, dedicated group of engineers and writers who have spent years working with audio generation tools.
No Corporate Backing
We operate independently, without corporate backing. Our API is a standalone service, not tied to larger tech giants, ensuring our focus remains on serving independent creators with straightforward tools and transparent pricing.
Developer Focused
Our API is built for developers who want to integrate TTS into their workflows. We provide a simple endpoint that mirrors the OpenAI speech endpoint, making it easy to generate audio files with just a few lines of code.
- Simple JSON API endpoint
- Compatible with OpenAI SDKs
- Easy integration for self-publishers
Voice Licensing
Our voices are based on the LibriTTS-R dataset.
LibriTTS-R Dataset
Our voices are derived from the LibriTTS-R dataset, offering a robust base for natural-sounding synthesis.
CC BY 4.0 License
The dataset operates under the Creative Commons Attribution 4.0 International License.
LibriVox Recordings
Each voice preset is based on licensed recordings from LibriVox public-domain audiobook readings. These real human recordings form the core of our synthetic voices, bringing authenticity to your text.
Data Policy
We believe in transparency about how your data is handled. When you send text to our API, it is used exclusively to generate the requested audio file. We do not use your input text to train or improve our models, ensuring your content remains yours.
The generated audio is returned in the response and is not stored on our servers. This means once you download your file, we have no copy of it. We only retain request metadata—such as timestamp, character count, and status—for accurate billing purposes.
Text Not Used for Training
Your input text is processed solely to produce the audio output. Unlike many other services, we do not ingest your manuscripts or scripts to train our neural networks. Your creative work remains distinct from our training data.
Audio Not Stored
Generated audio files are returned directly in the API response and are not stored on our servers. Once you retrieve the file, we hold no copy of your narration. This ensures your content is transient and under your control.
Metadata Kept for Billing
We keep request metadata, including time, character count, and status, to ensure accurate billing. This data is used strictly to calculate charges based on the $0.01 per 1,000 characters rate and to verify successful generations.
Technical Limits
TextReader Hub is built for batch processing, not real-time playback. You send text, and we return the final audio file. There is no WebSocket stream or partial audio chunks to consume live. This design keeps costs predictable and infrastructure simple for self-publishers generating full chapters.
No Streaming
Our API returns complete audio files (MP3, WAV, OPUS, FLAC, or PCM) upon successful synthesis. You cannot stream partial audio as it generates. This means you wait for the entire segment (up to 4,096 characters) to finish before receiving the file. It is ideal for audiobook production where you process chapters in batches rather than reading live on stage.
No SSML
We do not support Speech Synthesis Markup Language (SSML). You cannot inject tags for pauses, emphasis, or pronunciation changes directly into the request. Control is limited to the speed parameter (0.25–4.0) and voice selection. For precise timing, split your text manually into smaller segments and adjust speed per segment.
No Custom Cloning
We offer eight fixed voice presets based on licensed LibriTTS-R recordings. We do not provide custom voice cloning, so you cannot upload a sample to create a unique voice. You also cannot upload your own voice or design a new one. All generated audio includes an inaudible watermark identifying it as synthetic speech.

Support Contact
We keep things simple and direct. Our support team is reachable exclusively via email, allowing us to provide thoughtful, detailed answers to your technical questions without the noise of phone trees.
Email Only
Send your queries to our support address. We review every message carefully and respond with practical solutions tailored to your API integration needs.
No Phone
There is no phone number to call. This approach ensures that your support requests are logged and can be referenced later if needed, avoiding the hassle of waiting on hold.
No Live Chat
We do not offer live chat widgets. This allows our team to focus on resolving complex issues thoroughly rather than handling multiple brief, fragmented conversations simultaneously.
Affiliation
TextReader Hub is an independent storefront for the same underlying text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, or any other major brand mentioned in comparisons. Our service operates separately, using its own keys and billing system.
Not OpenAI
Our API endpoint and SDK compatibility mimic the OpenAI structure, but we are a distinct entity. We do not use OpenAI’s infrastructure or voice models. Requests sent to our domain are processed by our own engine.
Not ElevenLabs
While we offer similar narration capabilities for audiobooks, we are not ElevenLabs. Our voices are based on the LibriTTS-R dataset, not their proprietary models. Pricing and rate limits are set independently by us.
Independent Storefront
As an independent provider, we control our own key issuance and top-up methods via USDT. This page is a standalone storefront, not a sub-brand of a larger tech company. We focus solely on providing reliable TTS access for self-publishers.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Special attention is paid to consonant clarity and vowel shapes, ensuring that complex words are understood without distortion.
23 languages
Any voice speaks any of these languages.
