Frequently asked questions
How do I get an API key for the text to speech AI?
Navigate to /get-api-key/ and sign up using Google or an email and password. Your account page displays your active API key, current balance, and usage statistics. Each account maintains one active key, which can be regenerated at any time to invalidate the previous one immediately.
Is the OpenAI SDK compatible with this API?
Yes, the API uses the same request shape as the OpenAI speech endpoint. You can use official OpenAI SDKs by updating the base_url to https://api.playp94.com/v1 and providing your LingvoRead API key. This allows for straightforward integration without requiring custom HTTP client implementations for standard requests.
What is the base URL for the API?
The API base URL is https://api.playp94.com/v1. You send POST requests to https://api.playp94.com/v1/audio/speech for synthesis. Additional endpoints for voices and models are available at GET /v1/voices and GET /v1/models respectively. Ensure your SDK or HTTP client points to this exact domain.
Can I use the API for Japanese text to speech free?
Accounts created with Google sign-in receive a $0.50 free trial (about 50,000 characters) valid for 7 days. Accounts created with email and password do not receive trial credit. Japanese is supported, but usage consumes your available balance or trial credit at the standard rate.
How do I handle texts longer than 4096 characters?
Split your input text into segments of up to 4096 characters each. Send each segment as a separate request to the speech endpoint. Once you receive the audio files for all parts, concatenate them to produce the final audio output. This ensures compliance with the single-request character limit.
What audio formats are supported?
The API supports mp3, wav, opus, flac, and pcm response formats. Specify your preferred format in the response_format field of your request body. All generated audio files are returned directly in the API response, allowing immediate download or storage without intermediate processing steps required by the service.
Does the API support streaming audio?
No, the API does not support streaming or WebSocket connections for real-time partial audio. It returns complete audio files upon request completion. Requests are processed sequentially, so longer texts may experience queue delays. You must wait for the full synthesis to finish before receiving the audio data.
How do I authenticate requests?
Include your API key in the Authorization header using the Bearer scheme. The format is Authorization: Bearer tts-<your-key>. Each account has one active key. If you generate a new key, the previous one becomes invalid immediately. Ensure your key is sent with every request to the endpoint.
What happens if I exceed the rate limit?
The limit is 60 requests per minute per key, or 10 per minute before the first top-up. Exceeding this limit may result in request delays or rejections. Requests are processed sequentially, so under load, additional requests may queue. Monitor your usage via the account dashboard to avoid interruptions.
Is SSML supported in the request body?
No, the API does not support SSML (Speech Synthesis Markup Language). You provide plain text in the input field. There are no phoneme dictionaries or custom pronunciation lexicons available. The system guesses the language based on the script if the language field is not explicitly set.
Can I specify the language explicitly?
Yes, you can provide an optional ISO language code in the request body. If omitted, the system guesses the language, defaulting to English for Latin script. Explicitly setting the language is recommended for non-English Latin-script text to ensure accurate synthesis across the 23 supported languages.
How do I track my API usage?
Visit the /get-api-key/ page to view your current balance, characters remaining, and usage history. The system retains request metadata for billing purposes. You can monitor your consumption to manage your budget effectively, especially since pricing is based on the total character count processed.
What is the difference between tts-1 and tts-1-hd?
Both tts-1 and tts-1-hd use the same engine and incur the same price. The distinction is purely in the model identifier used in the request. There is no price difference between the two models. You may choose either based on your preference.
Are there SDKs for mobile platforms?
No, there is no official mobile SDK. You can use the official OpenAI SDKs or standard HTTP clients to integrate with the API on any platform. The API is designed to be platform-agnostic, allowing developers to build custom mobile integrations using standard web technologies.
First request
curl
curl https://api.playp94.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.playp94.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.playp94.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 and Keys
Access the LingvoRead API by including a valid Bearer token in the Authorization header of every request. The token authenticates your account against the endpoint at https://api.playp94.com/v1.
Keys are generated upon account creation and remain active until manually rotated. Use the key provided in your dashboard to authorize text-to-speech requests.
Bearer Token Usage
Include your key in the header as Authorization: Bearer tts-<your-key>. This string authenticates all subsequent API calls.
Ensure the key is transmitted securely. The token grants full access to your account's balance and usage data.
- Format:
Authorization: Bearer tts-... - Valid for all endpoints
Single Key Per Account
Each account maintains exactly one active API key. This simplifies integration by removing the need to manage multiple credentials for a single service instance.
The key is visible on your /get-api-key/ dashboard page alongside your current balance and usage statistics.
Key Rotation Policy
You may issue a new key at any time via the dashboard. Upon generation, the previous key becomes invalid immediately.
This ensures that if a key is compromised, you can revoke access instantly without waiting for a periodic cycle.
Old keys do not retain usage history; request metadata is kept for billing purposes.
- Old key stops at once
- No grace period
Speech Endpoint Specification
The POST /v1/audio/speech endpoint accepts text input and returns synthesized audio. This endpoint processes requests, returning the audio file directly in the response body. Clients send a JSON payload containing the text, voice selection, and format preferences, receiving a binary audio stream or file upon success.
Requests are processed sequentially. Under load, a request may wait in a queue before synthesis begins. The system handles long texts by splitting them into parts of up to 4096 characters and joining the resulting audio files. This ensures consistent delivery even for extended documents typical in audiobook production.
POST /v1/audio/speech
Send a POST request to https://api.playp94.com/v1/audio/speech. The endpoint accepts standard JSON bodies compatible with the OpenAI speech format. Authentication is required via the Authorization: Bearer header using your unique API key.
JSON Body Structure
The request body must be a valid JSON object. It includes the model identifier, the input text, the target voice, the desired audio format, and an optional speed multiplier. All fields are processed server-side to generate the final audio file.
model: "tts-1" or "tts-1-hd"input: Text string, max 4096 charactersvoice: One of 8 preset voicesresponse_format: mp3, wav, opus, flac, or pcmspeed: Float between 0.25 and 4.0language: Optional ISO 639-1 code
Required Fields
The model, input, and voice fields are mandatory. The input field contains the raw text to be converted. If the language field is omitted, the system guesses the language based on the script, defaulting to English for Latin text.

Voice and Model Parameters
The API supports two model variants, tts-1 and tts-1-hd, which utilize the identical synthesis engine and pricing structure. Selecting either model yields the same engine and price of $10 per 1 million characters.
Voice Selection Presets
Eight distinct voice presets are available, categorized by gender and tonal character. Female voices include aria (warm narrator), nova (bright), luna (soft storyteller), and sage (calm instructional). Male options feature felix (energetic), milo (conversational), atlas (neutral news), and orion (deep documentary).
Each voice supports all 23 listed languages, enabling consistent brand audio across localized content. The selection is defined by the voice parameter in the request body.
- aria: warm, clear narrator
- nova: bright, upbeat
- luna: soft, storytelling
- sage: calm, instructional
- felix: energetic, promo
- milo: friendly, conversational
Speed Control (0.25–4.0)
Adjust the speed parameter between 0.25 and 4.0 to modify playback rate. This allows fine-tuning of audio duration for specific content lengths or platform constraints without re-synthesis.
Audio Format Options
The API supports five output formats: MP3, WAV, Opus, FLAC, and PCM. Select the format that aligns with your ingestion pipeline’s codec requirements or storage constraints.
MP3, WAV, Opus, FLAC, PCM
MP3 and Opus provide compressed audio for efficient bandwidth usage. WAV and FLAC offer lossless quality, while PCM delivers raw uncompressed samples. Choose based on whether your downstream service requires specific codec compatibility or minimal decoding latency.
- MP3: Standard compressed format.
- WAV: Waveform Audio File Format.
- Opus: High-efficiency compression.
- FLAC: Lossless compressed audio.
- PCM: Raw byte stream.
Format Selection Logic
Specify the response_format parameter in the request body. The API generates the audio file in the requested format immediately upon synthesis completion. No post-processing is required.
File Size Implications
Compressed formats like MP3 and Opus significantly reduce storage and transfer costs compared to WAV or FLAC. PCM files are largest due to lack of compression. Select lossless formats only if downstream processing requires bit-perfect fidelity.
Language Handling
LingvoRead supports 23 languages, enabling precise synthesis for global content localization. You can explicitly define the language using an ISO code in the request body, ensuring consistent voice output regardless of the input text's origin. This parameter is essential for multilingual projects where automatic detection might misinterpret mixed-script content.
ISO Code Specification
Pass the desired language code (e.g., 'fr', 'de', 'ja') in the language field. This overrides any automatic detection, guaranteeing the engine selects the correct phonetic rules for the specified voice. 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.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Automatic Script Detection
When the language field is omitted, the API infers the language from the text script. For example, Cyrillic characters trigger Russian synthesis, while Hangul triggers Korean. This feature simplifies integration for monolingual workflows where the input text consistently matches the target language.
Latin Script Defaulting
If the input text uses Latin script and no language is specified, the system defaults to English. This may cause pronunciation errors for non-English Latin-script texts (e.g., German or Spanish). Explicitly setting the language parameter is recommended for all non-English content to ensure accurate phonetic rendering.

Rate Limits and Quotas
Rate limits ensure stable synthesis performance for independent publishers. Each API key is capped at 60 requests per minute, with a temporary restriction of 10 requests per minute for new accounts before the first top-up.
60 Requests Per Minute
Standard accounts process up to 60 synthesis requests per minute. This limit applies per active key, allowing predictable throughput for batch audiobook production or localization pipelines.
10 Requests Before Top-Up
New accounts begin with a reduced quota of 10 requests per minute. This constraint lifts immediately upon completing the minimum $5 USDT (TRC-20) top-up.
Queue Behavior Under Load
Requests are processed sequentially. During high demand, synthesis may wait in a queue before generation begins. Expect slight delays for long texts, as generation speed averages roughly 25 characters per second of audio.
Error Handling
The API returns standard HTTP status codes to indicate request outcomes. A 200 OK response confirms successful audio generation, while 4xx errors indicate client-side issues such as authentication failures or invalid parameters. Server-side errors return 5xx codes.
HTTP Status Codes
Use 200 for success, 400 for bad requests, 401 for unauthorized access, and 429 for rate limit exceeded. The 429 error occurs when you exceed 60 requests per minute or the initial 10 requests before top-up.
Failed Request Refunds
If synthesis fails, the charge is returned in full. Character counts are not deducted for failed requests. Successful requests are charged immediately based on input length.
Input Validation Errors
Input text must not exceed 4096 characters. Unsupported voices or invalid speed values (outside 0.25–4.0) return a 400 error. Ensure the input field is present and within limits.
- 400: Invalid parameter or input too long
- 401: Invalid or missing API key
- 429: Rate limit exceeded

OpenAI SDK Compatibility
LingvoRead’s speech endpoint mirrors the OpenAI API structure, allowing direct integration using existing OpenAI client libraries. Developers only need to adjust the base_url configuration point to https://api.playp94.com/v1 while retaining the standard SDK methods for generating audio from text. This approach eliminates the need for custom HTTP client wrappers, ensuring immediate compatibility with established engineering workflows.
The request payload remains identical to the OpenAI tts-1 and tts-1-hd models. By passing the LingvoRead API key via the Authorization: Bearer header, the SDK handles JSON serialization and response parsing seamlessly. This compatibility supports rapid prototyping and reduces integration time for teams already familiar with OpenAI’s speech endpoints.
Base URL Modification
To use the OpenAI SDK with LingvoRead, modify the base_url property in your client configuration to https://api.playp94.com/v1. All other endpoint paths and request bodies remain unchanged.
This single configuration adjustment allows the SDK to route requests correctly without requiring any code refactoring or additional dependency installations.
- Set
base_urltohttps://api.playp94.com/v1 - Retain standard SDK methods for audio generation
- No proprietary client library required
Standard SDK Methods
The AudioClient or equivalent SDK class handles the POST request to /v1/audio/speech. Pass your tts-... API key in the authorization header.
Standard parameters like model, input, voice, response_format, and speed are supported natively. The SDK manages the JSON body structure exactly as defined in the API specification.
This ensures consistent behavior whether using Python, Node.js, or other supported languages within the OpenAI ecosystem.
- Use standard
AudioClientmethods - Pass API key via
Authorizationheader - Support for Python, Node.js, and other languages
Example Code Snippets
Below is a Python example demonstrating the configuration change:
```python
from openai import OpenAI
client = OpenAI(
base_url="https://api.playp94.com/v1",
api_key="tts-your-api-key-here"
)
with client.audio.speech.create(
model="tts-1",
voice="nova",
input="This text is processed via LingvoRead.",
response_format="mp3"
) as response:
with open("output.mp3", "wb") as f:
f.write(response.content)
```
This snippet illustrates the minimal changes required to switch from OpenAI to LingvoRead, maintaining identical input and output behaviors.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Self-publishing lets startups directly monetize their expertise by producing audiobooks for global audiences.
23 languages
Any voice speaks any of these languages.
