Frequently asked questions
What is a PDF text reader API?
AudioPress is a cloud text-to-speech API, not a PDF reader. You send plain text (up to 4096 characters) via a POST request and receive an audio file. For PDFs, extract the text first, then send it to our endpoint at https://api.playv9999.com/v1/audio/speech to generate narration.
How do I convert a PDF to an audiobook?
Extract text from your PDF, ensuring it is under 4096 characters per request. Send it to our API with your chosen voice and format. For longer novels, split the text into parts, generate each audio file, and join them. Our API handles the synthesis; you handle the file assembly.
Which voices are best for fiction audiobooks?
For fiction, try Luna (soft, storytelling) or Aria (warm, clear narrator). For energetic promos or dialogue, Felix works well. Male options like Milo (friendly) or Orion (deep, documentary) also suit various narrative tones. All voices support 23 languages, allowing consistent narration across different linguistic editions of your book.
Does the API support long novels?
Yes, but you must split text into chunks of up to 4096 characters per request. Generate audio for each part, then join the files. Generation speed is roughly real-time, so long novels will take time proportional to their length. Requests process sequentially, so high volume may introduce slight queue delays.
What 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 supported language. If you omit the language field, it guesses from the script, defaulting to English for Latin text.
How is pricing calculated?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with charges returned in full. There are no monthly plans, seats, or minimum spends. Your balance never expires, and you only pay for the characters you actually generate.
Can I use my own voice?
No, we do not offer custom voice cloning or uploading your own voice. We provide eight preset voices based on licensed recordings from LibriTTS-R and LibriVox. Each generated file includes an inaudible watermark marking it as synthetic speech. You cannot design custom voices or upload audio files to create a unique voice model.
Is the audio file copyrighted?
The voices are based on licensed recordings (LibriTTS-R CC BY 4.0 and LibriVox public domain). Generated audio files carry an inaudible watermark indicating synthetic speech. While the API returns the file immediately, specific copyright status depends on the source voice license. We do not store generated audio, returning it only in the response.
Do you support SSML?
No, we do not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You send plain text input, and the API synthesizes it using the selected voice and speed parameters. There are no emotion tags or advanced markup options. For precise control, you may need to split text or adjust speed manually.
What happens if the request fails?
If synthesis fails, the charge is returned in full. You are not billed for unsuccessful requests. This ensures you only pay for successfully generated audio files. If you encounter persistent issues, contact us via email. We do not offer an SLA or uptime guarantee, so occasional failures may occur under load.
How long does generation take?
Generation is roughly real-time, producing about 25 characters of text per second of audio. Short phrases take a few seconds. Long texts require splitting and joining, which adds processing time. Requests are processed sequentially, so under heavy load, your request may wait in a queue before synthesis begins.
Can I stream the audio?
No, we do not support streaming, WebSocket, or real-time partial audio. You send a POST request with text and receive the complete audio file in the response. The file is returned immediately upon completion but is not stored on our servers. You must download the full file to use it.
Do you offer volume discounts?
No, there are no volume discounts, monthly plans, or tiered pricing. The rate is fixed at $10 per 1 million characters for all users. There are no seats or minimum spends. Your balance does not expire, and you can top up as needed without committing to a larger upfront amount.
How do I top up my account?
Top up using USDT on the TRON network (TRC-20) only. The minimum top-up is $5. Credits are added automatically within minutes after your transfer. We do not accept cards, PayPal, or invoices. You can manage your key and balance on the /get-api-key/ page after signing in with Google or email.
First request
curl
curl https://api.playv9999.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.mp3From Manuscript to Audiobook
AudioPress transforms your manuscript into professional audiobook audio via a reliable TTS API. Send text and receive an audio file, handling the narration heavy lifting so you can focus on your story. With speeds around 25 characters per second, long texts generate in near real-time.
Convert Text to Audio
Send your text to our API and receive high-quality audio instantly. We handle the synthesis engine, delivering mp3, wav, opus, flac, or pcm files directly in the response.
Handle Long Texts Seamlessly
Split texts into parts of up to 4096 characters and join the audio files automatically. Requests are processed sequentially, so under load a request may wait in a queue.
Choose Your Narrator
Select from 8 distinct voice presets, from warm narrators to energetic promos. Each voice offers a unique tone to match your book’s genre and mood.
Professional Voices for Your Story
AudioPress provides eight distinct voice presets designed to bring your manuscript to life. Each voice offers a unique tone, allowing you to match the narration style precisely to your book’s genre and mood.
Female Narrators
Aria delivers a warm, clear narration ideal for literary fiction. Nova brings a bright, upbeat energy perfect for contemporary romances or light reads. Luna offers a soft, storytelling quality suited for fantasy, while Sage provides a calm, instructional voice great for non-fiction or self-help.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
Male Narrators
Felix adds energetic drive to promotional content or fast-paced thrillers. Milo sounds friendly and conversational, making it ideal for memoirs or casual narratives. Atlas maintains a neutral, news-style tone for serious topics, while Orion provides a deep, documentary-style voice for historical or epic works.
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Distinct Personalities
Every voice is based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. This foundation ensures natural, human-like cadence without the uncanny valley effect. You can freely mix voices across chapters to represent different characters, creating a dynamic audio experience.
- Based on licensed recordings
- Natural cadence
- Mix voices for characters
Global Reach with Multilingual Support
Publish your audiobooks globally with native-quality narration in 23 languages. From English and Spanish to Arabic, Hindi, and Turkish, our TTS API ensures your story reaches listeners worldwide.
Whether you are publishing a thriller in German or a romance in Japanese, our engine delivers audio that respects the nuances of each language.
23 Supported Languages
We support 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, giving you full flexibility in casting your narrators.
None
- Full coverage of major global markets
- Support for diverse scripts and phonetics
- No extra cost for multilingual content
Auto-Detection and Manual Override
If you do not set a language, the API guesses from the script (Latin text defaults to English). For non-English Latin-script text, always set the language field to ensure accurate pronunciation.
You can explicitly define the language in your request to override detection, ensuring consistent delivery even for mixed-language passages or specific regional accents.
Cross-Language Consistency
Every voice maintains its distinct character across all 23 languages. You can cast 'Aria' for your English chapters and still use her for French or Spanish translations.
This consistency helps listeners recognize your narrators regardless of the language, building trust and familiarity with your work.
Fair Pricing for Publishers
AudioPress uses a simple, character-based pricing model that scales directly with your production volume. You pay only for the text you actually convert, making it easy to predict costs for short stories or full-length novels.
Pay Per Character
The rate is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, ensuring you never pay for wasted effort.
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. You top up with USDT (TRC-20) when needed, and your balance never expires. This structure fits irregular publishing schedules perfectly.
Free Trial Credit
Sign up with Google to receive $0.50 in credit, enough for about 50,000 characters. This trial lasts for 7 days.
Technical Reliability
AudioPress integrates smoothly with your existing development workflow. By using the standard OpenAI-compatible endpoint, you can leverage official SDKs simply by adjusting the base URL to our API domain.
We support multiple output formats to suit different distribution needs. Whether you require widely compatible MP3 files or lossless FLAC for archival quality, the API handles the conversion instantly, delivering ready-to-use audio files directly in the response.
OpenAI Compatible SDK
Use the official OpenAI SDKs with a simple configuration change. Set the base_url to https://api.playv9999.com/v1 and use your AudioPress key.
The request shape mirrors the standard speech endpoint, accepting model, input, voice, response_format, and speed parameters. This consistency reduces integration time for developers already familiar with common TTS patterns.
- Compatible with official OpenAI SDKs
- Simple
base_urlconfiguration - Standard JSON request body
Multiple Audio Formats
Choose from MP3, WAV, OPUS, FLAC, or PCM based on your project requirements. MP3 offers efficient storage, while FLAC ensures pristine audio quality for high-end releases.
Each request returns the audio file directly, eliminating the need for secondary download steps.
- MP3, WAV, OPUS, FLAC, PCM support
- Direct file response
- Format flexibility for distribution
Standard Rate Limits
Your API key allows up to 60 requests per minute, ensuring steady processing for batch operations. New accounts start with a limit of 10 requests per minute, which increases automatically after the first top-up.
This predictable scaling allows you to plan your generation capacity accurately. Long texts are processed sequentially, maintaining consistency in audio quality and timing.
- 60 requests per minute after top-up
- 10 requests per minute initially
- Predictable scaling for batch jobs

How It Works
Convert your manuscript into an audiobook by sending text to our API. You can paste content directly into the request body. Each request handles up to 4,096 characters, ensuring consistent quality even for long chapters.
Upload or Paste Text
Split longer texts into segments of 4,096 characters or less. Our API processes these sequentially, so you can generate full books by chaining requests. This approach keeps memory usage low and ensures every word is narrated clearly.
- Max 4,096 characters per request
- Supports plain text input
- Sequential processing for long novels
Select Voice and Language
Choose from eight distinct voices like Aria for warm narration or Felix for energetic promos. Set the language explicitly (e.g., 'en', 'de') to avoid auto-detection errors, especially with mixed scripts. The API guesses Latin script as English by default.
- 8 preset voices available
- 23 supported languages
- Adjustable speed (0.25–4.0x)
Receive Audio File
Receive your audio file immediately in MP3, WAV, OPUS, FLAC, or PCM format. The response contains the binary audio data, which you can save directly to your storage. Each file includes an inaudible synthetic watermark for verification.
- Multiple format outputs
- Instant binary response
- Inaudible watermark included
Why Indie Authors Choose Us
Indie authors need a narration engine that scales with their catalog, not their budget. AudioPress charges strictly by character count, so producing a 100,000-word novel costs the same per word whether it’s your first or your hundredth title. This linear pricing model eliminates the risk of unpredictable monthly bills as your backlist grows.
Cost Effective Scaling
Unlike services that charge per voice or per project, our flat rate of $0.01 per 1,000 characters ensures predictable costs. You can generate entire series without negotiating volume discounts or worrying about tiered pricing caps. The API handles the volume, letting you focus on writing and marketing.
- Flat rate: $0.01 per 1,000 characters
- No per-voice or per-project fees
- Predictable costs for series and backlists
Instant Turnaround
Generate audio in near real-time. With typical speeds of roughly 25 characters per second, you can produce chapters quickly without waiting for human voice actors. Short phrases take just a few seconds, and longer texts process sequentially, allowing you to batch-produce entire books overnight.
- Rapid generation: ~25 chars/sec
- Batch process multiple chapters
- No booking delays for talent
No Hidden Costs
Failed requests are free, so you only pay for successful audio files. There are no subscriptions, no seat limits, and no hidden fees for formats or languages. You top up with USDT when needed, and your balance never expires, giving you full control over your production spend.
- Failed requests are free
- No monthly subscriptions or seats
- Balance never expires
Data and Privacy
Your manuscript’s intellectual property remains yours. We use your input text solely to generate the audio file and do not train our models on your content, ensuring your stories stay unique to your brand.
No Training on Your Text
Unlike many platforms, we do not retain your input text for model improvement. Once the audio is generated and returned, the source text is not stored for training purposes, preserving your creative rights.
Synthetic Watermarking
Every audio file produced carries an inaudible watermark. This digital signature clearly marks the content as synthetic speech, helping platforms and listeners identify AI-generated narration without affecting audio quality.
- Invisible digital signature embedded in audio
- Clear identification of synthetic voice
- No impact on listening experience
Secure API Keys
Each account is issued a single active Bearer key. You can regenerate this key at any time via your dashboard. The previous key stops working immediately, ensuring your API access remains secure and under your control.
Get Started Today
Start by signing up via Google on our /get-api-key/ page to instantly receive $0.50 in trial credit. This allows you to generate approximately 50,000 characters of audio without entering payment details, perfect for testing your first chapter.
Once registered, your unique API key is displayed immediately alongside your balance and usage stats. You can copy this key to use with standard OpenAI SDKs or simple HTTP requests, ready for integration into your publishing workflow.
Sign Up with Google
Click the sign-in button on the homepage to authenticate with your Google account. This creates an independent account on playv9999.com and instantly grants you $0.50 in credit, valid for seven days.
- Instant account creation
- No credit card required
- 50,000 character trial credit
Get Your API Key
Navigate to the /get-api-key/ dashboard to view your active key. You can issue a new key at any time, which immediately invalidates the previous one, ensuring secure access for your scripts.
- Bearer token authentication
- Instant key rotation
- One active key per account
Test Your First Chapter
Use the provided curl example or OpenAI SDK to send your text to the /v1/audio/speech endpoint. Select a voice like 'aria' or 'nova' and receive a downloadable audio file within seconds.
- POST request to /v1/audio/speech
- Support for multiple formats
- Immediate audio generation
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Language support and format quality directly impact accessibility.
23 languages
Any voice speaks any of these languages.
