Frequently asked questions
Is this a Natural Readers alternative?
AudioPage is a cloud text-to-speech API alternative to Natural Readers. It converts text to audio via HTTP requests without installation. Supporting 23 languages and 8 voices, it offers a flexible, scalable solution for authors. Unlike subscription-heavy apps, it charges per character with no monthly limits, allowing you to generate audiobooks directly through simple API calls.
What is text-to-speech for authors?
Text-to-speech (TTS) converts written manuscripts into spoken audio files. For authors, this means turning your book into an audiobook format without hiring voice actors. You control the voice, speed, and language. The API processes your text and returns an audio file you can distribute, making self-publishing more accessible and affordable.
How much does it cost to convert a book?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. A typical novel might cost a few dollars depending on length. Failed requests are free. You pay only for what you generate, with no monthly subscriptions or minimum spend requirements.
Which voices are best for fiction?
For fiction, try Luna for soft storytelling or Aria for a warm, clear narrator. Milo offers a friendly, conversational tone suitable for dialogue-heavy scenes. Atlas provides a neutral news style, while Orion adds depth for dramatic moments. Each voice supports all 23 languages, allowing you to match the tone of your narrative.
Can I use the audio commercially?
Yes. Our voices are based on LibriTTS-R (CC BY 4.0) and public-domain LibriVox recordings, supporting commercial use. The API does not impose licensing restrictions on the generated output. You can incorporate the audio into your audiobooks, podcasts, or other commercial works. The audio is returned in the response and not stored by the service.
Do I need to code to use this?
No, you do not need to code. While the core product is an API, we provide a dashboard where you can manage your key and view usage. You can also use ready-made curl examples or the OpenAI SDK by changing the base URL. Many no-code tools can integrate with this API easily.
How many languages are supported?
We support 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. If you do not set the language, it guesses from the script, defaulting to English for Latin text.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files. You can retry the request or adjust parameters like speed or voice if needed, without financial penalty for errors during the processing stage.
Are the voices realistic?
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. They are clear and natural but carry an inaudible watermark marking them as synthetic. They are not celebrity clones. The quality is suitable for audiobooks and narration, offering a professional sound without the high cost of human voice actors.
Can I generate long texts?
Yes. Split your text into parts of up to 4096 characters and join the resulting audio files. Generation takes roughly real-time (about 25 characters per second). Requests are processed sequentially, so under load, a request may wait in a queue.
Is there a character limit?
Each API request accepts up to 4096 characters in the input field. For longer texts, you must split the content into chunks of this size. Each chunk generates a separate audio file that you can concatenate. This limit applies per request, not per account, allowing you to process entire books over multiple calls.
How do I pay for the service?
Top up via USDT (TRC-20) on the TRON network. Minimum deposit is $5, credited automatically within minutes. We do not accept credit cards, PayPal, or invoices. Your balance never expires. New Google sign-ups receive a $0.50 free trial (approx. 50,000 characters) valid for 7 days. Email/password accounts start without trial credit.
Do I own the generated audio?
The generated audio is returned in the response and not stored by our servers. Input text is used only to produce the audio and is not used for training. Since you control the generation process via the API, you retain the resulting audio files. The product facts do not claim ownership restrictions on the output.
Can I use this for YouTube?
Yes, you can use the generated audio for YouTube videos. The service provides MP3, WAV, Opus, FLAC, and PCM formats, all suitable for video platforms. Since the audio is generated on demand and not stored by us, you can download the file and upload it directly to your YouTube channel as your content.
First request
curl
curl https://api.playk74.com/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.mp3Why Authors Choose TTS
Generating audiobooks manually is time-consuming. Our API lets you convert manuscripts into audio files without writing code. You keep full control over the process, turning your text into listenable content in minutes rather than days.
There is no minimum order size. Whether you are publishing a short story or a full novel, the workflow remains the same. You simply send your text and receive the audio file, making it ideal for self-published authors.
Save time on narration
Synthesis runs at roughly real time—about 25 characters per second. While a full book may take hours to generate, the process is fully automated. You can upload your manuscript and let the API handle the conversion while you focus on marketing.
Requests are processed sequentially, meaning heavy traffic may introduce queue delays. This ensures consistent quality without requiring complex infrastructure on your end.
- Convert manuscripts to audio without recording studios
- Automated generation for long-form content
- No technical skills required
No minimum order size
Traditional narration services often require large upfront commitments. Our model scales with your needs. Generate a single chapter or an entire series without locking yourself into expensive packages or minimum volume requirements.
This flexibility allows you to test different voices and formats with small samples before committing to the full book production.
Pay only for what you use
Start with a free trial including $0.50 credit. After that, you pay just $0.01 per 1,000 characters. Failed requests are free, so you only pay for successful audio generation.
Balance does not expire, and there are no monthly fees. Top-up is available via USDT on the TRON network, processed automatically within minutes.
- $0.01 per 1,000 characters
- No monthly subscriptions
- Failed requests are free
Voice Selection
We offer eight distinct voice presets designed for audiobook narration and self-publishing. Each voice is based on licensed recordings from LibriTTS-R and LibriVox public-domain readings, providing a clear and natural sound for your manuscripts.
8 realistic presets
Select from eight high-quality voices tailored for different narrative styles. Our library includes distinct character options, allowing you to choose the perfect tone for your book's genre, whether it is a calm instructional guide or an energetic promotional read.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
- Felix: Energetic, promo
- Milo: Friendly, conversational
Male and female options
Our voices are categorized by gender to suit diverse storytelling needs. Female presets include Aria, Nova, Luna, and Sage, while male options feature Felix, Milo, Atlas, and Orion. This variety helps you maintain consistent character voices across long chapters.
- Atlas: Neutral, news
- Orion: Deep, documentary
Consistent tone
Each preset maintains a stable tonal quality throughout your text. Unlike variable AI models, our licensed recordings ensure that the voice remains uniform from the first page to the last, reducing the need for extensive post-production editing in audiobook production.

Language Support
Support 23 languages including English, Spanish, French, German, and Japanese. Any voice can speak any supported language, making it easy to produce multilingual content.
23 languages available
We support 23 languages, including Arabic, Chinese, Danish, Dutch, Finnish, Greek, Hebrew, Hindi, Italian, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, and Turkish. Every voice preset can speak all supported languages, giving you consistent audio quality across your entire catalog.
Automatic language detection
The API guesses the language from your text’s script. Latin text defaults to English. For non-English Latin-script text, explicitly set the language parameter to ensure accurate pronunciation.
Multi-language books
Generate separate audio files for each language segment. This approach keeps files manageable and allows listeners to choose their preferred language. We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, or Bengali.
Audio Formats
Choose the output format that matches your distribution needs. Our API supports MP3, WAV, OPUS, FLAC, and PCM, giving you precise control over file size and quality without complex conversion tools.
MP3 for easy sharing
MP3 is the standard for web playback and most audiobook platforms. It offers a small file size that loads quickly on any device, making it ideal for blog posts or social media clips.
WAV for high quality
WAV provides uncompressed audio, preserving every detail of the synthesis. This format is perfect for professional masters, local editing, or archiving where you need the highest fidelity without data loss.
FLAC for archival
FLAC offers lossless compression, reducing file size significantly compared to WAV while keeping audio quality identical. It is the best choice for long-term storage of your manuscript recordings, saving disk space without compromising sound.
Pricing Model
Our pricing is straightforward: you pay only for the text you convert. The rate is $10 per million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward this total. If a synthesis request fails, you are not charged, ensuring you only pay for successful audio generation.
Pay per character
Each request processes up to 4,096 characters. For longer manuscripts, split your text into parts and join the resulting audio files. There is no minimum spend or per-request fee, making it cost-effective for both short chapters and full-length books.
- Rate: $10 per 1,000,000 characters
- Failed requests are free
- Spatial and punctuation characters count
No monthly fees
We do not offer subscriptions, seats, or tiered plans. Your balance does not expire. When you need to add funds, top up with USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes after the transfer.
- No monthly subscriptions
- No minimum spend
- USDT (TRC-20) top-ups only
Free trial included
New accounts created via Google sign-in receive a $0.50 trial credit, valid for 7 days. This covers approximately 50,000 characters, allowing you to test voice quality and integration without immediate payment. Email-based accounts start without trial credit.

Technical Simplicity
Turn manuscripts into audio without writing code. Our API mirrors the OpenAI speech endpoint, so you can reuse existing libraries and examples. Just change the base URL and use your key. This compatibility means you avoid learning a new protocol or building custom clients from scratch.
Works with OpenAI SDK
Use the official OpenAI SDKs by pointing them to our API base URL. The request shape is identical, so you can swap in our endpoint without rewriting your integration logic.
Easy API integration
Send a POST request with your text, voice, and format preferences. The API returns the audio file directly. You can also list available voices and models via simple GET requests.
No complex setup
Start generating audio immediately after signing up. You get a valid API key instantly, with no need for custom contracts or technical onboarding. Just handle character limits (4096 per request) and combine the resulting audio files.
Data Privacy
When you send your manuscript for synthesis, we use your input text strictly to generate the audio file. Your words are not added to our datasets, nor are they used to train or improve our models. This ensures your unpublished stories or unique voice remain yours, keeping your creative work private and secure from model development cycles.
Text not used for training
Unlike many consumer platforms, we do not ingest your input text to build our training data. The text you submit for conversion is processed solely for that specific generation task and is kept separate from the data used to develop the TTS engine.
No stored audio
Generated audio is returned in the response and not stored. Once you download your file, the server does not keep a copy of the synthesized speech. This means your audio files are transient, reducing the risk of your content being accessed from our storage later.
Secure generation
We retain request metadata—such as time, character count, and status—only for accurate billing purposes. This minimal data ensures you are charged correctly without retaining unnecessary copies of your creative output. All transfers are secured via standard HTTPS protocols.
Common Use Cases
Authors can convert manuscripts into audio files by splitting text into 4,096-character segments and joining the results. Since voices are based on licensed recordings, the output remains consistent throughout long texts.
This workflow requires no complex setup or specialized equipment, making it accessible for self-publishing creators.
Audiobook creation
Convert manuscripts into audio files by splitting text into 4,096-character segments and joining the results. Since voices are based on licensed recordings, the output remains consistent throughout long texts.
Choose from eight presets like Aria for narration or Atlas for news-style reading. Each request generates a file ready for distribution.
- Split long texts into 4,096-character parts
- Join audio files seamlessly
- 8 voice presets for different tones
- Consistent voice across segments
Blog post audio
Generate audio versions of blog posts quickly. Paste the text into the API and receive an MP3 or WAV file.
Use the free trial credit to test short phrases before publishing full posts.
- Convert blog posts to audio
- Support for multiple languages
- Fast generation for short content
- Easy integration with websites
Educational content
Create audio lessons for students using clear voices like Sage for instructional content. Supports 23 languages for global reach.
No minimum order size allows you to generate small amounts of content for free trials or specific modules.
- Clear instructional voices
- 23 languages supported
- No minimum order size
- Ideal for e-learning

Get Started
Start by creating an account on the get-api-key/ page. You can sign in with Google to receive an immediate free trial credit, or use a standard email and password. This creates your independent storefront identity.
Sign up for free
Account creation is instant. If you use Google sign-in, you receive $0.50 in trial credit valid for 7 days, allowing you to generate about 50,000 characters. Email-based accounts start without trial credit but are fully functional.
Get your API key
Once registered, you are issued one active API key. You can view your balance, usage statistics, and a ready-to-use cURL example directly on the dashboard. If needed, you can issue a new key at any time, which immediately invalidates the previous one.
- One active key per account
- Instant key revocation on reissue
- Visible usage and balance dashboard
Generate your first file
Use the provided cURL example or the OpenAI SDK by pointing it to the API base URL. Send your text via a POST request to the speech endpoint. You will receive an audio file in your chosen format, such as MP3 or WAV.
- Use standard cURL examples
- Compatible with OpenAI SDKs
- Receive MP3, WAV, Opus, FLAC, or PCM
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Turn your written words into immersive audio stories without writing a single line of code today
23 languages
Any voice speaks any of these languages.
