Frequently asked questions
How do I get an API key?
Sign up on the /get-api-key/ page using Google or email. Accounts created with email start without trial credit, while Google sign-ins receive $0.50 valid for 7 days. You can issue a new key anytime; the old one stops immediately.
What is the base URL for the API?
The API base URL is https://api.playv9999.com/v1. Use this for all requests, including the speech endpoint POST https://api.playv9999.com/v1/audio/speech. Ensure your Authorization header uses your specific Bearer token.
Do I need to install a specific SDK?
No proprietary SDK is required. You can use the official OpenAI SDKs by changing the base_url to https://api.playv9999.com/v1. Alternatively, use plain HTTP requests to interact with the API endpoints directly.
Can I use the OpenAI Python SDK?
Yes. The API accepts the same request shape as OpenAI. Configure the OpenAI Python SDK by setting the base_url to https://api.playv9999.com/v1 and providing your API key. It works seamlessly with standard methods.
What models are available?
Two models are available: tts-1 and tts-1-hd. Both use the same engine and pricing. Select your preferred model in the request body to generate high-quality audio from your text input efficiently.
How do I change the voice?
Specify the voice parameter in your request body. Choose from eight presets: aria, nova, luna, sage, felix, milo, atlas, or orion. Each voice supports all 23 languages, allowing flexible narration styles for your audiobooks.
What audio formats are supported?
Supported formats include mp3, wav, opus, flac, and pcm. Set the response_format field in your request to your preferred output type. This ensures compatibility with various audiobook distribution platforms and editing workflows.
What is the rate limit?
The limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so high load may cause queuing delays during generation.
How do I handle errors?
Failed requests are free, with the charge returned in full. Check the response status for errors. Ensure your text is under 4096 characters and your key is valid. Use the /v1/models endpoint to verify available resources.
Does the API support streaming?
No, the API does not support streaming, WebSocket, or real-time partial audio. You send text and receive the complete audio file in the response. This fits batch processing workflows typical for audiobook production.
Can I send SSML?
No, SSML is not supported. The API accepts plain text input up to 4096 characters. It does not offer phoneme dictionaries or custom pronunciation lexicons. Use standard text formatting for your narration needs.
How do I split long texts?
Split your text into parts of up to 4096 characters. Send each part to the API and join the resulting audio files. This ensures efficient processing while staying within the single-request character limit.
Is the API compatible with other OpenAI clients?
Yes, it uses the same request shape as OpenAI. Official OpenAI SDKs work by changing the base_url to https://api.playv9999.com/v1. This allows you to use familiar client libraries with minimal configuration changes.
How do I rotate my API key?
You can issue a new key at any time via your account dashboard. When a new key is issued, the old one stops working immediately. This ensures secure access control without downtime for your applications.
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.mp3Python (openai)
from openai import OpenAI
client = OpenAI(base_url="https://api.playv9999.com/v1", api_key="tts-...")
with client.audio.speech.with_streaming_response.create(
model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
response.stream_to_file("hello.mp3")Node.js (openai)
import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({ baseURL: "https://api.playv9999.com/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));| voice | |
|---|---|
aria | female |
nova | female |
luna | female |
sage | female |
felix | male |
milo | male |
atlas | male |
orion | male |
| language | |
|---|---|
ar | العربية |
zh | 中文 |
da | Dansk |
nl | Nederlands |
en | English |
fi | Suomi |
fr | Français |
de | Deutsch |
el | Ελληνικά |
he | עברית |
hi | हिन्दी |
it | Italiano |
ja | 日本語 |
ko | 한국어 |
ms | Bahasa Melayu |
no | Norsk |
pl | Polski |
pt | Português |
ru | Русский |
es | Español |
sw | Kiswahili |
sv | Svenska |
tr | Türkçe |
Authentication
Access the AudioPress API by creating an account at /get-api-key/. You can sign in with Google or use an email and password. Your dashboard displays your unique API key, current balance, and a ready-to-use cURL example for immediate testing.
Each account holds one active key at a time. This single key authenticates all your requests to the speech generation endpoint. Manage your credentials directly from the dashboard to keep your audiobook production workflow secure and simple.
Generate Your API Key
Navigate to the /get-api-key/ page to create your account. Signing in with Google grants a $0.50 free trial valid for 7 days, allowing you to test the service immediately. Email-based accounts start without trial credit but can top up easily.
Once registered, your dashboard displays your active API key, current balance, and usage statistics. You can copy this key directly into your scripts or applications to begin generating audio files.
- Sign up via Google for instant trial credit ($0.50)
- Email/password accounts start with zero balance
- Dashboard shows key, balance, and usage stats
Bearer Token Format
Include your API key in the request header using the standard Bearer token scheme. The header must be formatted exactly as: Authorization: Bearer tts-... . This token authenticates every POST request to the speech endpoint.
Ensure no extra spaces or characters are included in the token value. The system validates the key before processing any text synthesis, so an invalid or expired key will result in an authentication error.
- Format: Authorization: Bearer tts-...
Key Rotation Policy
Rotate your key anytime from the dashboard. When you issue a new key, the previous one stops working immediately. This ensures that if a key is compromised, you can revoke access instantly without waiting for a cooldown period.
Only one key is active per account at any given time. This simplifies security management for indie authors who may share credentials temporarily with collaborators or CI/CD pipelines during production.
- Issue new key from dashboard
- Old key stops immediately
- One active key per account
Endpoints Overview
The API provides three core endpoints to manage your audiobook production workflow. You use the speech endpoint to convert text into audio, the voices endpoint to browse available narrators, and the models endpoint to verify engine details.
These endpoints work together to let you fetch voice options, select the right model, and generate high-quality audio files efficiently for your self-publishing projects.
Speech Generation Endpoint
POST to /v1/audio/speech to convert your manuscript text into audio. Send a JSON body with the text, voice, and format. The endpoint returns the audio file directly in the response.
This is your primary workhorse endpoint. Ensure your text is under 4,096 characters per request to avoid splitting logic.
- Endpoint: POST /v1/audio/speech
- Returns: Audio file in requested format
List Voices Endpoint
GET /v1/voices returns a list of all available voices, their languages, and supported formats. Use this to preview options before generating your first chapter.
Check this endpoint to see which voices support the specific language of your manuscript, such as German, Japanese, or Spanish.
- Endpoint: GET /v1/voices
- Returns: Voice IDs, languages, and formats
Model Information Endpoint
GET /v1/models provides details about the underlying TTS engines. You can verify that 'tts-1' and 'tts-1-hd' are available.
This endpoint helps you confirm model availability and ensure your integration is using the correct engine versions for consistent audio quality.
- Endpoint: GET /v1/models
- Returns: Model IDs and details
First Request with cURL
Once you have your API key, generating an audiobook chapter is a single HTTP request. The API accepts your text and returns an audio file, handling the synthesis engine for you. This direct approach lets you integrate narration into your publishing workflow without managing complex infrastructure.
You only need to specify the text, the voice you prefer, and your output format. The system handles the rest, delivering a ready-to-use audio file that you can immediately upload to your preferred distributor.
Basic JSON Body
Send a POST request to the speech endpoint with a JSON payload. The body must include the model, input text, voice selection, and desired response format. Keep your chapter under 4,096 characters to ensure immediate processing.
model: "tts-1" or "tts-1-hd"input: Your chapter text (max 4096 chars)voice: One of the 8 available presetsresponse_format: mp3, wav, opus, flac, or pcm
Required Fields
The input field carries your manuscript text. Spaces and punctuation count toward the character limit, so ensure your text is clean before sending. The voice field determines the narrator’s tone, while response_format defines the file type you receive.
Example Response
On success, you receive a binary audio stream. Failed requests are free, so you can safely retry without worrying about credit deduction. Save the output directly to an .mp3 or .wav file for your audiobook project.
Using the OpenAI SDK
The OpenAI SDK offers a convenient way to integrate AudioPress into your audiobook workflow, as our API mirrors the standard speech endpoint structure. By simply adjusting the base URL, you can leverage existing libraries to handle audio generation without writing custom HTTP clients.
This approach allows self-publishers to quickly prototype chapter narration using familiar Python or Node.js code, reducing the time spent on boilerplate integration.
Install the SDK
Install the official OpenAI client library using your preferred package manager. For Python environments, use pip to add the necessary dependency to your project.
pip install openai
Set Base URL
Configure the SDK to point to our API endpoint. Initialize the client with your API key and set the base URL to https://api.playv9999.com/v1. This ensures all requests route through AudioPress infrastructure.
client = OpenAI( api_key="tts-your-api-key", base_url="https://api.playv9999.com/v1" )
Code Example
Generate audio for a book chapter by passing your text, voice selection, and format preferences. The SDK handles the JSON serialization and returns the audio file directly.
audio = client.audio.speech.create( model="tts-1", voice="nova", input="Chapter One: The Beginning...", response_format="mp3" ) audio.stream_to_file("chapter1.mp3")
bullets
Voice Selection
Choosing the right voice is critical for audiobook immersion. Our eight presets cover diverse narrative styles, from warm narrators to deep documentary tones. Each voice is engineered to handle long-form text with consistent pacing and clarity, ensuring your listeners stay engaged chapter after chapter.
Selecting a voice that matches your book’s genre helps maintain tonal consistency. Whether you are writing a fast-paced thriller or a gentle children’s story, there is a preset designed to deliver the appropriate emotional texture without needing complex configuration.
Available Presets
We offer eight distinct voices, categorized by gender and tone. Female voices include Aria (warm narrator), Nova (upbeat), Luna (storytelling), and Sage (instructional). Male options feature Felix (energetic), Milo (conversational), Atlas (neutral news), and Orion (deep documentary).
All voices support the full range of 23 languages. You can mix voices across chapters if your narrative style demands it, though consistency is usually preferred for long-form content.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Voice Characteristics
Each voice is derived from licensed recordings, ensuring natural prosody and clear articulation. They are optimized for spoken word, avoiding the robotic cadence often found in less refined TTS systems.
The voices are static presets; you cannot adjust pitch or emotion manually. This simplicity ensures reliable, batch-ready audio generation for your entire manuscript.
Language Matching
While any voice can speak any of the 23 supported languages, setting the language field is crucial for non-English Latin-script texts. Without it, the system guesses English for Latin characters, which may cause mispronunciation.
Supported languages include Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.

Audio Formats
The API returns audio in multiple formats to suit different publishing workflows. MP3 is the standard for most audiobook platforms due to its balance of quality and file size, making it ideal for distribution to listeners.
Choose WAV or FLAC when you need lossless quality for editing or archival purposes. These formats preserve the full fidelity of the synthesized voice without compression artifacts.
MP3 Support
MP3 is a common choice for self-published audiobooks. It provides clear narration while keeping file sizes manageable for storage and streaming.
WAV and FLAC Options
WAV offers uncompressed audio for immediate editing, while FLAC provides lossless compression for smaller storage footprint without quality loss. Both are suitable for master files before conversion to streaming formats.
Use these when you plan to add background music or sound effects in post-production.
- WAV: Uncompressed, widely compatible.
- FLAC: Lossless compression, smaller than WAV.
PCM and Opus
PCM provides raw audio data for custom processing pipelines. Opus is efficient for low-bandwidth streaming scenarios, offering good quality at low bitrates.
Select PCM or Opus if your specific delivery channel requires these specific codecs.
- PCM: Raw audio data.
- Opus: Efficient streaming codec.
Rate Limits and Performance
Understanding rate limits and generation speed helps you plan your audiobook production workflow effectively. Knowing how requests are processed ensures you can estimate delivery times for long-form texts without unexpected delays.
Our system processes requests sequentially, meaning performance depends on current load. This section details how to manage concurrency and optimize your narration pipeline for consistent results.
Requests Per Minute
Each API key is limited to 60 requests per minute. New accounts start with a lower limit of 10 requests per minute until the first top-up is completed.
This limit applies per key, so rotating keys or managing multiple projects requires careful planning to stay within the quota.
- Standard limit: 60 requests/minute
- Initial limit: 10 requests/minute
- Limit resets per key
Queue Behavior
Requests are processed one after another. If you send multiple requests simultaneously, they will wait in a queue.
Under heavy load, a request may experience delays before processing begins. Plan your submission timing to minimize wait times.
- Sequential processing
- Queue-based waiting
- No guaranteed latency
Generation Speed
Typical speed is roughly real-time for long texts (about 25 characters of text per second of generation).
Short phrases may take a few seconds to process. Factor in queue wait time when estimating total production duration.
For texts longer than 4096 characters, split the text into parts and join the resulting audio files.
- ~25 chars/sec for long texts
- Short phrases: few seconds
- Split text >4096 chars
Error Handling
Errors are handled with clear HTTP status codes so you can programmatically manage synthesis failures. Failed requests are free, ensuring you are never charged for audio that wasn’t generated.
Common Error Codes
Use standard HTTP codes to diagnose issues. A 401 Unauthorized indicates an invalid or expired API key. A 429 Too Many Requests signals you have exceeded the 60 requests per minute limit.
Retry Strategy
Implement exponential backoff for 429 and 500 errors. Since requests are processed sequentially, short waits often resolve temporary queue delays. Retry failed requests immediately as they are free.
Character Limit Errors
Each request accepts up to 4,096 characters. Exceeding this limit returns a 400 Bad Request. Split long chapters into smaller parts and join the resulting audio files in your workflow.
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.
