Text-to-Speech API Documentation for Developers

By AudioPage editorial team · Updated 2026-11-18

This guide helps independent authors and developers integrate AudioPage’s text-to-speech API into their audiobook workflows. You will learn how to generate audio files from manuscripts using standard HTTP requests, without needing to learn Python or manage complex infrastructure. The documentation covers authentication, endpoint usage, and voice selection with concrete examples.

We focus on practical steps for converting text into speech using the tts-1 and tts-1-hd models. You will find ready-to-use curl commands, integration tips for the official OpenAI SDKs (by changing the base URL), and details on available formats like MP3 and WAV. This page is designed for users who want direct control over audio generation for their self-published works.

Text-to-Speech API Documentation for Developers

Frequently asked questions

What is the API endpoint?

Send POST requests to https://api.playk74.com/v1/audio/speech with a JSON body containing your text, voice selection, and format preferences.

How do I get an API key?

Sign up at /get-api-key/ using Google or email. Your key starts with 'tts-'. You can issue a new key anytime, which instantly invalidates the old one.

Does it work with OpenAI SDK?

Yes. Use the official OpenAI SDKs by changing the base_url to https://api.playk74.com/v1 and providing your site-specific key via the Authorization header.

What languages can I use?

Support covers 23 languages including English, Spanish, French, German, Japanese, and Chinese. Any voice can speak any supported language. Vietnamese and Thai are not supported.

How do I send a request?

POST JSON to the speech endpoint. Include 'model' (tts-1 or tts-1-hd), 'input' (text up to 4096 chars), 'voice', 'response_format', and optional 'speed' or 'language'.

What formats are supported?

You can choose mp3, wav, opus, flac, or pcm via the 'response_format' field. MP3 is efficient for web use, while WAV offers uncompressed quality.

What are the rate limits?

You get 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. Failed requests count toward limits.

Can I change the speed?

Yes. Use the 'speed' field with values between 0.25 and 4.0. Default speed is 1.0. Adjusting speed helps match the pacing of your manuscript.

How do I handle errors?

If synthesis fails, the charge is returned in full. Check your request body for valid fields like voice name and character limits under 4096 characters.

Is the API documented?

Yes. This page serves as the quickstart. Use GET /v1/voices to list available voices, languages, formats, and prices. Use GET /v1/models to check model details directly via the API. For full integration details, see the /docs/ page.

Can I use Python?

Yes. Use the OpenAI Python SDK or plain HTTP libraries. Change the base_url to https://api.playk74.com/v1 and pass your 'tts-...' key in the headers.

Can I use JavaScript?

Yes. Use the OpenAI JavaScript SDK or fetch API. Set the base URL to https://api.playk74.com/v1 and include your Bearer token in requests.

How do I list voices?

Send a GET request to /v1/voices. This returns details on all 8 voice presets, their styles, supported languages, and available audio formats for your audiobooks.

What is the base URL?

The API base URL is https://api.playk74.com/v1. All endpoints, including speech synthesis and voice listing, are prefixed with this domain path.

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.mp3

Python (openai)

from openai import OpenAI

client = OpenAI(base_url="https://api.playk74.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.playk74.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
ariafemale
novafemale
lunafemale
sagefemale
felixmale
milomale
atlasmale
orionmale
language
arالعربية
zh中文
daDansk
nlNederlands
enEnglish
fiSuomi
frFrançais
deDeutsch
elΕλληνικά
heעברית
hiहिन्दी
itItaliano
ja日本語
ko한국어
msBahasa Melayu
noNorsk
plPolski
ptPortuguês
ruРусский
esEspañol
swKiswahili
svSvenska
trTürkçe

Authentication

Sound wave illustration for: Authentication

To use the AudioPage API, you must first obtain an API key from your account dashboard. Sign in via Google or email at /get-api-key/ to view your unique key, current balance, and usage statistics.

Include this key in every request using the standard Bearer token format. You can generate a new key at any time; the old one stops immediately, ensuring secure access control.

Get your API key

Navigate to /get-api-key/ on playk74.com. Select Google or email registration. Your active key appears immediately alongside your balance and character count.

  • Google Sign-In grants a $0.50 free trial (7 days)
  • Email accounts start with zero credit
  • Keys are unique per site account

Bearer token format

Send your key in the HTTP header as: Authorization: Bearer tts-... . This format ensures compatibility with standard HTTP clients and the OpenAI SDK.

Key management

You may issue a new key at any time. The previous key becomes invalid instantly. This allows quick revocation if your key is exposed.

Endpoint Basics

Sound wave illustration for: Endpoint Basics

The core of the API is the POST https://api.playk74.com/v1/audio/speech endpoint. Send your manuscript text here to receive a generated audio file.

POST speech endpoint

Send a JSON payload to the endpoint above. The API processes up to 4096 characters per request and returns the audio file directly in the response.

JSON body structure

The request body requires standard fields compatible with the OpenAI speech endpoint. You must include the model, input text, and voice selection.

Required fields

Include model ("tts-1" or "tts-1-hd"), input (your text), voice (one of the 8 presets), and response_format (mp3, wav, opus, flac, or pcm). The speed and language fields are optional.

Endpoint Basics

Curl Example

Sound wave illustration for: Curl Example

This section demonstrates how to generate audio using the command line. You will send a POST request to the speech endpoint with your API key and text payload.

Basic request

Send your text to https://api.playk74.com/v1/audio/speech. Include the model, voice, and input text in the JSON body. Use Bearer authentication with your key.

  • Endpoint: POST /v1/audio/speech
  • Header: Authorization: Bearer tts-...

Command line usage

Use curl for quick testing. Replace YOUR_API_KEY with your actual key. Set the text length under 4096 characters.

  • curl -X POST https://api.playk74.com/v1/audio/speech
  • -H "Authorization: Bearer YOUR_API_KEY"
  • -H "Content-Type: application/json"
  • -d '{"model": "tts-1", "voice": "nova", "input": "Hello world"}'

Response handling

The API returns the audio file directly in the response body. Save this output to a file on your local machine.

  • Response format: audio/mp3
  • Save to file: > output.mp3

OpenAI SDK

Sound wave illustration for: OpenAI SDK

The official OpenAI SDKs work with AudioPage by changing the base_url to https://api.playk74.com/v1 and providing your API key. This allows you to use familiar tools without writing a custom library from scratch.

Below are quick examples for Python and JavaScript to help you integrate the API into your workflow.

Base URL change

Update your SDK client configuration to point to https://api.playk74.com/v1. Use your Bearer token for authentication. This ensures all requests go to our endpoint while keeping the standard request shape.

  • Base URL: https://api.playk74.com/v1
  • Auth: Authorization: Bearer tts-...

Python integration

Install the standard openai library. Initialize the client with your base URL and key. Call client.audio.speech.create() with your text, voice, and model parameters.

JavaScript usage

Install the openai npm package. Configure the client with the base URL and API key. Use client.audio.speech.create() to generate audio files from your text input.

Response Formats

Sound wave illustration for: Response Formats

The API returns audio files in five supported formats, allowing you to choose between file size and quality for your audiobook projects. Each response contains the raw binary audio data, which you can save directly to your storage or process further.

MP3 format

MP3 is a widely compatible format. It provides efficient compression, making it ideal for web distribution and standard audio players. This format reduces bandwidth usage while maintaining acceptable audio quality for most listening scenarios.

WAV format

WAV offers uncompressed, lossless audio quality. It is larger than MP3 but ensures no data loss during generation. This format is suitable for professional editing workflows or archival purposes where peak fidelity is required.

Other formats

You can also request Opus, FLAC, or PCM. Opus provides high-quality compression at lower bitrates than MP3, useful for efficient storage. FLAC offers lossless compression, smaller than WAV but retaining full quality. PCM provides raw, uncompressed audio data, useful for immediate playback or further processing without decoding overhead.

  • Opus: Efficient compression, good for storage
  • FLAC: Lossless compression, smaller than WAV
  • PCM: Raw, uncompressed audio data
Response Formats

Voice Selection

Sound wave illustration for: Voice Selection

Choose from eight distinct voice presets designed for audiobook narration. Each voice offers a specific tone, from warm narrators to calm instructional guides, ensuring your manuscript finds the right auditory personality.

List available voices

Select from eight presets: aria, nova, luna, and sage (female); felix, milo, atlas, and orion (male). These voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain readings.

  • 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 parameters

Pass the voice name directly in the voice field of your request. The system accepts any of the eight presets without additional configuration.

Language setting

Specify the language using an ISO code. If omitted, the system guesses the language from the text script (defaulting to English for Latin script). Explicitly set the language field for non-English Latin text to ensure accuracy.

  • Supported: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Rate Limits

Sound wave illustration for: Rate Limits

Each API key allows 60 requests per minute, with a lower limit of 10 requests per minute for new accounts before the first top-up. Requests are processed sequentially, meaning under load a request may wait in a queue before synthesis begins.

Requests per minute

Rate limits apply per key. If you exceed the limit, subsequent requests will be rejected until the window resets. Failed requests count toward this limit.

  • Standard limit: 60 requests/minute

Queue behavior

Requests are processed one after another. For long texts that require splitting into chunks, each chunk counts as a separate request. This sequential processing ensures order but may introduce delays during high traffic periods.

Limit exceptions

New accounts start with a reduced limit of 10 requests per minute. This increases to 60 requests per minute automatically after the first top-up of at least $5 via USDT (TRC-20). There are no other exceptions or upgrades.

Rate Limits

Error Handling

Sound wave illustration for: Error Handling

Handling errors correctly ensures you only pay for successful audio generation. Failed requests are free, with the charge returned in full if synthesis fails.

Understanding these behaviors helps you manage your $0.01 per 1,000 characters cost efficiently without unexpected charges for incomplete files.

Common errors

Errors typically stem from exceeding the 4,096 character limit or invalid voice IDs. A 429 status indicates you have hit the 60 requests per minute limit.

  • 400: Invalid JSON or missing required fields like input or voice.
  • 401: Invalid or expired API key.
  • 429: Rate limit exceeded (60 requests/minute).
  • 500: Internal server error during synthesis.

Retry logic

Implement exponential backoff for 429 or 500 errors. Since requests are processed sequentially, a brief pause often resolves queue delays.

  • Wait 1–2 seconds before retrying on 429 errors.
  • Retry once on 500 errors with a 2-second delay.

Refund process

If a request fails, the character count is not deducted from your balance. No manual claim is needed; the credit is automatically restored.

  • Failed requests incur zero cost.
  • Balance updates reflect failed attempts immediately.

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

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. LibriTTS-R corpus (OpenSLR 141)
  3. IETF RFC 7845: Ogg Opus
  4. Tether (USDT)
  5. LibriVox public-domain audiobooks
  6. FFmpeg documentation
  7. MDN: Web Speech API
  8. Node.js documentation
  9. Python documentation
  10. Creative Commons Attribution 4.0
  11. openai-python on GitHub
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site