Cloud Text-to-Speech API for Restaurant Voice Integration

By MenuVoce editorial team · Updated 2026-11-19

This guide provides the technical documentation for integrating MenuVoce’s cloud Text-to-Speech API into restaurant menu boards, digital kiosks, and multilingual announcement systems. You will find precise instructions on authentication, request formatting, and voice selection to ensure clear, professional audio playback for your dining hall operations.

The documentation covers essential integration steps including cURL examples, OpenAI SDK configuration, and language handling for 23 supported languages. It details rate limits, error codes, and audio format options so you can reliably deploy synthetic voice announcements that match your brand’s tone and operational requirements.

Cloud Text-to-Speech API for Restaurant Voice Integration

Frequently asked questions

What is the endpoint URL for the TTS API?

The endpoint is POST https://api.cv66bet.info/v1/audio/speech. Send a JSON body containing your text, voice selection, and other parameters to generate audio files for your restaurant announcements or menu items.

How do I set the language to Hindi in the request?

Include the language parameter set to the ISO code for Hindi in your JSON request body. This ensures the synthetic voice correctly pronounces Hindi text, which is essential for multilingual menu guides.

Does the API support streaming audio in real-time?

No, the API does not support streaming, WebSocket, or real-time partial audio. You send a request and receive the complete audio file once generation finishes.

What is the maximum character limit per request?

The maximum character limit per request is 4096 characters. For longer menus, you must split the text into parts of this size and join the resulting audio files programmatically.

Can I use the OpenAI Python SDK with this API?

Yes, the official OpenAI SDKs work by changing the base_url to https://api.cv66bet.info/v1 and using your site's key. This allows you to use standard libraries without installing custom SDKs.

How do I handle rate limit errors in my restaurant app?

The limit is 60 requests per minute per key. If you exceed this, implement retry logic with exponential backoff in your app to wait until the quota resets, ensuring smooth operation during peak hours.

Is the audio format selectable in the API request?

Yes, you can select mp3, wav, opus, flac, or pcm via the response_format field. Choose formats that best fit your digital signage or audio player systems for clear restaurant announcements.

What happens if the synthesis fails mid-process?

If synthesis fails, the charge is returned in full. Failed requests are free, so you do not lose credits if the audio generation process encounters an error during processing.

Do I need to install any specific libraries?

No specific library is required beyond standard HTTP clients or the OpenAI SDK. We do not provide an official proprietary SDK, so you can use any tool that supports JSON over HTTPS.

Is the API key shared across all my restaurant locations?

You have one active key per account. This single key can be used across all your restaurant locations, as the rate limit applies per key, not per physical location.

Can I generate audio in multiple languages in one request?

No, each request generates audio for a single language specified by the voice and language parameters. To create multilingual content, you must send separate requests for each language needed.

How do I rotate my API key securely?

Issue a new key from your account dashboard at any time. The old key stops working immediately, ensuring secure rotation without downtime for your restaurant's voice integration systems.

Is there a way to get a preview of the audio before saving?

The API returns the generated audio file in the response. You can then save or play it.

What is the speed range for voice generation?

The speed range is 0.25 to 4.0. Adjusting speed allows you to match the tone of your restaurant, from calm narration to energetic promotional announcements, within these defined limits.

First request

curl

curl https://api.cv66bet.info/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.cv66bet.info/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.cv66bet.info/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 and Keys

Sound wave illustration for: Authentication and Keys

Access the MenuVoce API by registering at /get-api-key/ using Google or email. The dashboard displays your active API key, current balance, and usage statistics immediately upon login.

Getting Your API Key

Getting Your API Key

Create an account to receive your unique Bearer token. New Google sign-ups receive a $0.50 trial credit valid for 7 days, allowing immediate testing without payment setup.

  • Sign up via Google or email/password
  • View key and balance on dashboard
  • $0.50 trial credit for Google accounts

Bearer Token Authorization

Bearer Token Authorization

Include your key in the HTTP header as Authorization: Bearer tts-.... This single key authenticates all requests to the speech endpoint and tracks your character consumption.

Key Rotation Policy

Generate a new key at any time via the dashboard. The previous key becomes invalid immediately upon creation of the new one, ensuring secure access management for your restaurant's voice systems.

Quick Start with cURL

Sound wave illustration for: Quick Start with cURL

Use the endpoint POST https://api.cv66bet.info/v1/audio/speech to generate audio. Send a JSON body with your API key in the Authorization header to receive an audio file.

Basic POST Request Example

Send a simple request to generate speech. Replace YOUR_API_KEY with your key from the dashboard.

  • ```bash
  • curl -X POST https://api.cv66bet.info/v1/audio/speech \
  • -H "Authorization: Bearer YOUR_API_KEY" \
  • -H "Content-Type: application/json" \
  • -d '{"model": "tts-1", "input": "Welcome to our dining hall", "voice": "aria", "response_format": "mp3"}' \
  • -o menu_audio.mp3
  • ```

Required JSON Body Fields

The request body must include model, input, voice, and response_format. model accepts tts-1 or tts-1-hd. input is your text, up to 4096 characters. voice selects from eight presets like nova or atlas. response_format supports mp3, wav, opus, flac, or pcm.

Response Handling

The API returns the audio file directly in the response body. Save the output to a file for playback on kiosks or systems. Failed requests return an error object without charging your balance.

OpenAI SDK Integration

Sound wave illustration for: OpenAI SDK Integration

The API mirrors the OpenAI speech endpoint shape, allowing you to use official OpenAI SDKs by simply pointing base_url to https://api.cv66bet.info/v1. This compatibility lets restaurant operators integrate synthetic voice menus into existing Node.js or Python backend services without rewriting core logic.

Configuring base_url

Set the base_url configuration to https://api.cv66bet.info/v1 in your SDK client. This directs all requests to our infrastructure while maintaining standard OpenAI request structures. Ensure your API key is passed via the standard Authorization: Bearer header.

  • Base URL: https://api.cv66bet.info/v1
  • Standard Bearer token authentication
  • Compatible with OpenAI SDK request shapes

Using Official SDKs

Leverage the official OpenAI SDK for Node.js or Python. No custom client library is required. The SDK handles JSON serialization and HTTP transport automatically, reducing integration time for your development team.

  • Works with official OpenAI SDKs
  • No proprietary client needed
  • Standard HTTP/JSON transport

Code Snippets for Node.js

Initialize the client with your key and the adjusted base URL. Call the speech.create method with your chosen model (tts-1 or tts-1-hd), voice preset, and input text. The response returns the audio file directly for playback or storage.

  • Install official OpenAI SDK
  • Set base_url to our API
  • Use standard speech.create method

Voice Parameters and Selection

Sound wave illustration for: Voice Parameters and Selection

Choosing the right voice ensures your menu announcements and digital signage convey the correct brand tone. Our eight presets are categorized by gender and intended use case, allowing you to match the audio to your dining hall’s atmosphere.

Select voices based on clarity and warmth. Female options include Aria for clear narration, Luna for storytelling, and Sage for instructional guides. Male presets offer Felix for energetic promos, Milo for conversational tones, Atlas for neutral news, and Orion for documentary-style depth.

Selecting Female Voices (Aria, Nova, Luna, Sage)

Aria provides a warm, clear narrator style ideal for standard menu items. Nova offers a bright, upbeat tone suitable for promotional announcements. Luna delivers a soft, storytelling voice perfect for background ambiance. Sage is calm and instructional, best for detailed dietary information.

All female voices support all 23 languages, including Hindi, Spanish, and German. Select the voice that aligns with your establishment’s service style, whether casual or formal.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional

Selecting Male Voices (Felix, Milo, Atlas, Orion)

Felix is energetic and ideal for promotional offers or happy hour announcements. Milo provides a friendly, conversational tone for everyday updates. Atlas delivers a neutral, news-style voice for clear information delivery. Orion offers a deep, documentary-style tone for premium or historical descriptions.

Like female voices, male presets support all 23 languages. Use Felix for high-energy moments, Milo for general service, Atlas for clarity, and Orion for a sophisticated background presence.

  • Felix: Energetic, promo
  • Milo: Friendly, conversational
  • Atlas: Neutral, news
  • Orion: Deep, documentary

Setting Voice ID in JSON

Include the chosen voice ID in the voice field of your JSON request body. For example, use "voice": "nova" for bright announcements or "voice": "sage" for instructional guides. The API accepts lowercase voice IDs as listed.

Ensure the voice ID matches the desired tone. Incorrect IDs will result in an error. Test with short phrases to verify audio quality before full integration.

  • Use lowercase voice IDs
  • Match tone to brand
  • Test before full integration

Language Configuration

Sound wave illustration for: Language Configuration

Language configuration ensures your menu announcements and dining hall guides are delivered in the correct dialect. You can explicitly define the target language using an ISO code, or rely on our automatic detection system which analyzes the script of your input text.

ISO Language Code Parameter

Include the language field in your JSON body to force a specific output language. This is essential when your text uses Latin script but is not English, ensuring the AI selects the correct voice model for languages like French, German, or Spanish.

Auto-Detection Logic

If the language field is omitted, the API guesses the language based on the text script. Latin script defaults to English. CJK characters trigger the corresponding Asian language model. This simplifies integration for single-language menus but may misinterpret mixed-language signs.

Setting Hindi Language Code

To generate audio in Hindi, include "language": "hi" in your request. Hindi is fully supported across all eight voice presets. Ensure your input text matches the expected script for accurate pronunciation and natural intonation in your dining announcements.

  • Supported language code: hi
  • Applies to all 8 voice presets
  • Latin script defaults to English if unspecified
Language Configuration

Audio Formats Supported

Sound wave illustration for: Audio Formats Supported

The API returns audio files in five distinct formats, allowing you to optimize file size and playback quality for specific restaurant environments. Each format serves a different technical need, from web delivery to high-fidelity in-store broadcasting.

MP3 for Web and Kiosks

MP3 is the standard choice for HTML5 audio players and touch-screen displays. It offers a good balance between file size and quality, making it ideal for menu boards and waiting area announcements where bandwidth efficiency matters.

WAV for High Quality

Choose WAV when you need uncompressed audio. This format preserves the audio data, suitable for high-quality playback on premium in-store speakers where fidelity is prioritized over file size.

OPUS and FLAC Options

OPUS provides efficient compression for modern web applications, while FLAC offers lossless compression for archival purposes. PCM is also available for raw audio processing. Select the format that best fits your infrastructure's decoding capabilities.

Rate Limits and Quotas

Sound wave illustration for: Rate Limits and Quotas

For menu announcements and multilingual guides, consistent voice quality matters more than raw speed. MenuVoce’s API allows up to 60 requests per minute per active key.

60 Requests Per Minute

After topping up your account, you can process 60 requests per minute. This limit applies to all keys in your account. Since each request handles up to 4096 characters, you can generate substantial menu text or long announcements efficiently without hitting caps immediately.

  • Limit resets every 60 seconds.
  • Applies per API key, not per IP.
  • Sufficient for most daily menu updates.

10 Requests Per Minute (Pre-Top-Up)

New accounts start with a 10 requests per minute limit. This allows you to test voice clarity and language support before committing funds. Once you top up with USDT (TRC-20), the limit automatically increases to 60 requests per minute within minutes.

  • Applies until first top-up.
  • Use for testing voice presets.
  • Increases to 60 rpm after payment.

Handling 429 Errors

If you exceed the limit, the API returns HTTP 429 Too Many Requests. Implement exponential backoff in your integration to retry after a short delay. Failed synthesis requests do not consume your character quota, but rate limits still apply to the request count.

  • Return code 429.
  • Retry with exponential backoff.
  • Failed requests don't use character credit.

Error Handling and Codes

Sound wave illustration for: Error Handling and Codes

Our API returns standard HTTP status codes to indicate request outcomes. A 200 OK response confirms successful audio generation, while 400-level errors indicate client-side issues such as invalid parameters or authentication failures. Use these codes to direct your error-handling logic in restaurant management systems or digital signage networks.

Common HTTP Status Codes

A 401 Unauthorized error occurs if your Bearer token is missing or incorrect. A 429 Too Many Requests indicates you have exceeded the 60 requests per minute limit. A 500 Internal Server Error suggests a temporary backend issue; retry with exponential backoff.

  • 200: Success. Audio file returned.
  • 400: Bad Request. Invalid JSON or missing fields.
  • 401: Unauthorized. Check your API key.
  • 429: Rate limit exceeded. Wait and retry.

Handling Synthesis Failures

If synthesis fails due to a server error, the charge is returned in full. Your balance remains unaffected. Implement a retry mechanism for transient 5xx errors. For persistent failures, contact support via email.

  • Full refund for failed synthesis.
  • Retry on 5xx errors.
  • Email support with request ID.

Input Text Validation

Ensure your input text does not exceed 4096 characters per request. Text exceeding this limit will return a 400 error. Split longer menu descriptions or announcements into smaller chunks and concatenate the resulting audio files. This ensures consistent audio quality and prevents truncation.

  • Max 4096 characters per request.
  • Split long menus manually.
  • Concatenate audio files.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. For example, specify 'it' for Italian dishes to ensure correct intonation and clarity, even if the voice is English-based.

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. Python documentation
  3. curl documentation
  4. LibriTTS-R paper (arXiv 2305.18802)
  5. TRON developer hub: TRC-20
  6. LibriTTS-R corpus (OpenSLR 141)
  7. openai-python on GitHub
  8. MDN: Web Speech API
  9. Tether (USDT)
  10. Node.js documentation
  11. Creative Commons Attribution 4.0
  12. FFmpeg documentation

More on this site