Frequently asked questions
What is a text-to-speech API?
A text-to-speech API is a cloud service that converts written text into audio files. You send text via a simple POST request, and receive an audio file in return. It works like the OpenAI speech endpoint, allowing you to use standard SDKs by adjusting the base URL. This makes integrating narration into your publishing workflow straightforward and automated.
Which voices sound best for German text?
All eight voices support German. For narration, Luna offers a soft, storytelling tone, while Sage provides a calm, instructional style. Felix brings energetic energy suitable for promos, and Atlas delivers a neutral news-like delivery. You can choose any voice for German text; the API handles the pronunciation correctly regardless of the voice preset selected.
How much does it cost to read a book?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. For a typical 50,000-character manuscript, the cost is approximately $0.50. Failed requests are free, so you only pay for successfully generated audio files. This pay-as-you-go model ensures you only spend on actual usage.
Can I use this for commercial audiobooks?
Yes, this API is designed for self-publishers and audiobook creators. You can generate natural-sounding narration for commercial projects without hiring voice actors. The generated audio files are yours to use. There are no monthly plans or seat limits, making it easy to scale your production as your catalog grows.
What languages are supported besides German?
We support 23 languages including English, French, Spanish, Italian, Japanese, Korean, Chinese, Arabic, Hindi, Russian, Portuguese, Dutch, Danish, Finnish, Greek, Hebrew, Malay, Norwegian, Polish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. If you use Latin script for non-English texts, you should explicitly set the language parameter.
Do I need to be technical to use the API?
While it is an API, it is designed to be accessible. You can use ready-made curl examples or standard OpenAI SDKs. The /get-api-key/ page provides your key and balance details. For non-technical users, you can also use third-party tools that support standard TTS endpoints. No custom SDK or complex setup is required.
How long does it take to generate audio?
Generation is roughly real-time, averaging 25 characters per second of audio. Short phrases take a few seconds, while longer texts may take longer due to queueing. Requests are processed sequentially, so high load may cause delays. For very long books, splitting text into 4096-character parts ensures efficient processing and faster overall completion.
Is there a limit on text length per request?
Yes, each request can contain up to 4096 characters. If your manuscript is longer, you must split it into parts, generate audio for each, and join the files. This ensures consistent quality and manageable processing times. The API handles the conversion efficiently, but splitting is required for books exceeding this character limit.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for unsuccessful requests. This ensures you only pay for usable audio files. Failed requests do not consume your character allowance. You can retry the request or adjust parameters like speed or voice to resolve the issue and generate the audio.
How are the voices licensed?
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This means the source material is freely available. Each generated file carries an inaudible watermark marking it as synthetic speech. This licensing model allows for cost-effective production while respecting the original creators' rights.
Can I mix different voices in one audio file?
No, each request generates audio for a single voice. To mix voices, you must generate separate audio files for each voice and join them manually. The API does not support multi-voice tracks in a single response. This approach gives you full control over the narration structure and voice assignments for your audiobook.
Does the API support special characters?
The API handles standard text input, including special characters and punctuation. Spaces and punctuation count toward the character limit. The system processes text up to 4096 characters per request. The API does not support SSML. The engine intelligently handles most common characters and symbols in supported languages.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20). The minimum amount is $5. Credits are added automatically within minutes after your transfer. There are no monthly plans or subscriptions. Your balance does not expire. You can issue a new API key at any time, and the old one stops immediately.
Is my input text stored permanently?
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. Request metadata, such as time, characters, and status, is kept for billing purposes. Your data remains private and is not shared or used for other purposes.
First request
curl
curl https://api.44bd.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.mp3Turn Manuscripts into Audiobooks
Turn your manuscripts into listenable audio with our cloud API. Send text and receive an audio file in seconds. Whether you are producing a thriller or a memoir, the synthetic voice provides consistent narration, allowing you to maintain creative control over your project's tone.
Natural German Narration
Generate clear audio that respects the rhythm and flow of spoken language. The API handles up to 4096 characters per request, ensuring smooth transitions between chapters.
Multi-Language Support
Create audiobooks in 23 languages, including German, English, Spanish, and French. Any voice can speak any supported language, making it easy to localize your content.
Instant Generation
Receive audio files quickly. Requests are processed directly, and longer texts are split and joined automatically. Typical speed is roughly real time, so you can generate hours of content efficiently.
Voices That Tell Stories
Our eight voice presets are designed to match the tone of your manuscript, from warm storytelling to authoritative narration. Each voice is based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings.
You can choose from female and male presets to find the perfect fit for your audiobook, ensuring your content sounds professional and engaging without needing a studio.
Warm Narrator: Aria
Aria offers a warm, clear narration style perfect for fiction and memoirs. Her tone is inviting and easy to follow, making long listening sessions comfortable for your audience.
Use Aria to bring emotional depth to character-driven stories or personal essays.
- Ideal for fiction and memoirs
- Warm, clear narration
- Engaging for long sessions
Deep Documentary: Orion
Orion provides a deep, documentary-style voice that conveys authority and seriousness. It is ideal for non-fiction, historical accounts, or educational content.
His steady pacing helps maintain focus on complex information without distracting the listener.
- Deep, authoritative tone
- Perfect for non-fiction
- Steady, focused pacing
Upbeat Promo: Felix
Felix brings energy and enthusiasm to your audio, making him suitable for promotional material or lighter reading. His bright delivery keeps the pace moving.
Use Felix for short clips, advertisements, or upbeat segments within a larger project.
- Energetic and bright
- Great for promos
- Keeps the pace moving
Built for Self-Publishers
Self-publishing means you wear every hat, but your voice shouldn't be one of them. TextReader Hub lets you convert your manuscript into listenable audio without hiring expensive voice actors or learning complex software. Whether you are narrating your own work or preparing a project for others, the process is straightforward and reliable.
No Coding Required
Upload your text and generate audio instantly. You do not need to write scripts or manage servers. The API handles the heavy lifting, delivering natural-sounding narration in 23 languages, including German, so you can focus on your story.
- Direct text-to-audio conversion
- Supports up to 4096 characters per request
- Ready curl example for quick testing
Pay Per Character
Stop paying for monthly plans you might not use. You only pay for what you generate: $10 per million characters. Failed requests are free, so you never pay for errors. This model scales perfectly with your publishing output.
- Rate: $0.01 per 1,000 characters
- Balance does not expire
- Top up via USDT (TRC-20)
No Monthly Fees
There are no subscriptions, no seats, and no minimum spend. You keep your balance and use it whenever you need it. This flexibility is ideal for self-publishers who release books at their own pace, ensuring your costs align directly with your revenue.
- Zero monthly commitment
- No hidden costs
- Instant key issuance
Accessibility First
Accessibility is central to our mission. We ensure that every generated audio file is clear, natural, and easy to listen to, making your manuscripts accessible to a wider audience without requiring professional studio equipment.
Clear Audio Output
Our engine delivers clear narration. Each voice is carefully crafted to maintain consistent tone and pacing, ensuring your listeners stay engaged from the first page to the last.
Multiple Formats
Choose the format that fits your distribution channel. We support MP3, WAV, OPUS, FLAC, and PCM. Whether you need compressed files for web distribution or lossless audio for other uses, we have you covered.
Fast Processing
Generate audio quickly, even for longer texts. Typical speed is roughly real-time, producing about 25 characters of text per second. Short phrases take just a few seconds, letting you iterate on your narration style rapidly.
Technical Simplicity
The API follows the same request structure as the OpenAI speech endpoint. This means you can use the official OpenAI SDKs by simply changing the base_url to https://api.44bd.info/v1 and providing your site’s API key. It works for Python, Node.js, and other languages.
You don’t need a custom library or a complex setup. Just point your existing HTTP client to our endpoint and send standard JSON. This compatibility lets self-publishers integrate narration generation into their existing workflows without learning a new system.
OpenAI Compatible SDK
Use the official OpenAI SDKs with a simple configuration change. Set the base URL to https://api.44bd.info/v1 and use your tts-... key. This approach works seamlessly with popular languages like Python and JavaScript, allowing you to generate audio files with minimal code adjustments.
The request shape matches the OpenAI speech endpoint exactly. You pass text, voice, and format parameters, and receive an audio file in return. This standardization reduces integration time and lets you focus on your manuscript rather than API quirks.
- Works with official OpenAI SDKs
- Change only the
base_url - Supports Python, Node.js, and more
REST API Endpoint
Send a POST request to https://api.44bd.info/v1/audio/speech. Include your Authorization: Bearer key in the header. The API accepts text input and returns the generated audio file directly in the response.
For managing your account, use GET /v1/voices to list available voices, languages, and formats, or GET /v1/models to check available engines. These endpoints help you verify your options before generating audio.
POST /v1/audio/speechGET /v1/voicesGET /v1/models
Simple JSON Body
The request body uses standard JSON fields: model ("tts-1" or "tts-1-hd"), input (your text, up to 4096 characters), voice (e.g., "aria" or "orion"), and response_format (mp3, wav, opus, flac, or pcm). You can also set speed (0.25–4.0) and language (ISO code).
Keep it straightforward. No complex XML or custom headers. Just structure your text, choose a voice, and send it. The API handles the rest, delivering high-quality narration ready for your audiobook project.
model: "tts-1" or "tts-1-hd"input: up to 4096 charactersvoice: 8 presets availableresponse_format: mp3, wav, opus, flac, pcmspeed: 0.25–4.0language: optional ISO code

Transparent Pricing
Our pricing model is straightforward and scales with your output. You pay only for the characters you actually use, making it easy to budget for small projects or large libraries.
$10 Per Million Characters
The rate is fixed at $0.01 per 1,000 characters, including spaces and punctuation. This equates to roughly $10 for every million characters processed. Texts are split into parts of up to 4,096 characters, so costs are predictable per request.
- No per-minute audio fees
- No volume discounts required
- Balance never expires
Free Failed Requests
If synthesis fails, the charge is returned in full. You do not pay for audio that isn't generated, ensuring you only spend on successful outputs.
No Hidden Costs
There are no monthly plans, seats, or minimum spends. We do not charge for API key issuance or support. Payments are processed via USDT (TRC-20) with automatic credit.
- No VAT invoices
- No subscription fees
- No hidden transaction fees
Try It Yourself
Start your audiobook journey with zero risk. Create an account via Google to receive $0.50 in free trial credit, valid for 7 days. This provides approximately 50,000 characters to test voice quality and generation speed before committing funds.
Free Trial Credit
Sign up on our /get-api-key/ page to activate your trial instantly. No credit card is required to begin. Use this credit to experiment with different voices and languages, ensuring the tone fits your manuscript perfectly before you spend your own money.
- $0.50 trial credit upon Google sign-in
- Valid for 7 days
- Approximately 50,000 characters of generation
- No credit card required
Demo Audio Samples
Hear the difference between our eight presets. Listen to Aria for warm narration or Orion for deep documentary styles. Each sample demonstrates the natural flow and clarity suitable for self-published audiobooks, helping you choose the right voice for your story.
- Listen to Aria (warm narrator)
- Hear Orion (deep documentary)
- Sample Felix (energetic promo)
- Test Nova (bright and upbeat)
Quick Start Guide
Generate your first audio file in minutes. Use the ready-made curl example on your dashboard or our OpenAI-compatible SDK. Split long texts into 4,096-character chunks and receive MP3 or WAV files directly in your response.
- Copy the ready curl example
- Use OpenAI SDK with base_url change
- Split text into 4,096-char chunks
- Receive MP3, WAV, OPUS, FLAC, or PCM
Why Choose Us?
We prioritize transparency and trust in every audio file we generate. Our voice models are built from licensed recordings, ensuring that your narrations are created with proper data provenance rather than scraped from the open web.
Each output carries an inaudible synthetic watermark, clearly marking the content as AI-generated for publishers and platforms that require disclosure. Support is by email only for any questions about your files or billing.
Licensed Voice Data
Our eight voice presets are based on licensed recordings from the LibriTTS-R dataset, sourced from LibriVox public-domain audiobook readings. This foundation ensures high-quality, consistent narration without the legal ambiguity of unverified voice data.
- Based on LibriTTS-R (CC BY 4.0)
- Sourced from LibriVox public-domain readings
- Consistent voice quality across projects
Synthetic Watermarking
Every audio file generated through our API contains an inaudible watermark. This subtle marker identifies the content as synthetic speech, which is increasingly required by audiobook distributors and platforms for transparency with listeners.
- Inaudible digital watermark in every file
- Identifies content as AI-generated
- Meets emerging platform disclosure standards
Email Support
We offer straightforward email support for all account and billing questions. There are no phone queues or live chat bots; just a direct line to our team who can help you resolve issues quickly.
- Direct email contact
- No phone or live chat
- Assistance with billing and keys
Get Started Today
Creating your first audiobook starts with a quick account setup. Sign up using your Google account or email to receive your unique API key immediately, with no credit card required for the initial trial credit.
Sign Up with Google
Visit the /get-api-key/ page and click the Google sign-in button. Your account is created instantly, granting you access to the dashboard and a $0.50 free trial credit valid for 7 days.
Generate API Key
Once logged in, your active API key is displayed on the dashboard. This key authenticates your requests to the API. You can generate a new key at any time, which immediately invalidates the previous one for security.
Start Narrating
Use the provided curl example or OpenAI SDK to send your manuscript text. The API returns audio files in your chosen format, ready for download and distribution to your readers.
- Send text up to 4096 characters per request
- Receive audio in MP3, WAV, OPUS, FLAC, or PCM
- Start with the $0.50 trial credit
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.
