Frequently asked questions
What is a free voice generator text to speech API?
It is a cloud API where you send text and receive an audio file. The endpoint matches the OpenAI speech endpoint shape, allowing you to use standard SDKs by changing the base URL. It requires a Bearer token for authentication and processes requests sequentially to generate speech from text inputs.
Can I use TTS for digital menu boards in restaurants?
Yes, the API generates audio files suitable for playback systems. You can specify formats like mp3, wav, opus, flac, or pcm. The generated audio is returned in the response and not stored, making it ideal for on-demand announcements or menu item descriptions without long-term storage dependencies.
How much does the restaurant TTS API cost?
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 a full charge return. There are no monthly plans, seats, or minimum spends, allowing you to pay only for what you generate.
Which voices sound best for food announcements?
All eight voices support every language, so suitability depends on your specific use case rather than a single "best" option. Aria offers a warm, clear narrator tone, while Nova provides a bright, upbeat style. Felix delivers an energetic promo feel, and Milo ensures a friendly, conversational voice. Atlas remains neutral for news-style updates, and Orion adds a deep, documentary style for premium descriptions.
Does the API support multiple languages for diverse dining halls?
Yes, it supports 23 languages including English, Spanish, French, German, Chinese, Japanese, and Arabic. Any voice can speak any of these languages. If the language is not set, it is guessed from the script, though you should explicitly set it for non-English Latin-script text to ensure accuracy.
Is there a limit on characters per request?
Yes, each request accepts up to 4,096 characters of input text. For longer texts, you should split them into parts of this size and join the resulting audio files. This limit applies to the JSON body input field when sending your POST request to the speech endpoint.
Can I use the audio files for commercial restaurant advertising?
Yes, the API generates synthetic speech files that you can use for commercial purposes. Every generated file carries an inaudible watermark that marks it as synthetic speech. The input text is not used for training, and the generated audio is returned in the response, giving you full control over the output.
How fast is the audio generation speed?
Generation is roughly real-time on long texts, processing about 25 characters per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue before synthesis begins. You can adjust speed between 0.25 and 4.0.
Do I need to pay for failed requests?
No, failed requests are free. If synthesis fails, the charge is returned in full to your account balance. You only pay for successful audio generations. This ensures you are not penalized for temporary issues or invalid inputs that prevent the API from producing the final audio file.
Is there a free trial available for startups?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. You can top up with USDT on the TRON network to continue using the service after the trial expires.
Can I integrate this API with my existing restaurant management software?
Yes, the API uses a standard JSON body similar to the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base URL to https://api.playak56.com/v1. This allows easy integration with existing software stacks that support standard HTTP requests and JSON data formats.
What audio formats are supported for playback systems?
The API supports mp3, wav, opus, flac, and pcm response formats. You can specify the desired format in your request. These formats cover most digital signage and playback systems used in restaurants, ensuring compatibility with various hardware setups for menu boards and announcement speakers.
How do I manage my API key for the restaurant service?
You manage your key via the /get-api-key/ page on the site. Each account has one active key, and you can issue a new key at any time, which stops the old one immediately. The page displays your key, balance, usage, and a ready curl example for testing.
Are the voices based on real human recordings?
Yes, the voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark that marks it as synthetic speech. No custom voice cloning or emotion tags are available for these presets.
First request
curl
curl https://api.playak56.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.mp3TTS for Restaurant Operations
SavorVoice provides a lightweight text-to-speech API tailored for restaurant tech startups. By converting text into clear audio files, you can automate menu descriptions, waiting room updates, and table notifications without complex infrastructure.
Digital Menu Announcements
Replace static digital signage with dynamic audio. Send dish descriptions via POST request and play the resulting MP3 or WAV file on loop screens.
Waiting Room Audio
Keep guests informed about wait times or special offers. Use the API to generate announcements that play on waiting area speakers, reducing perceived wait times.
Table Notification Sounds
Trigger audio cues when a table is ready or an order is complete. Integrate with your POS system to send text inputs and receive audio files instantly.
Available Voices for Hospitality
Selecting the right voice is critical for clear communication in busy dining environments. Our API provides eight distinct voice presets, each optimized for specific hospitality use cases, from menu readings to table notifications.
Warm Narrator (Aria)
Aria offers a warm, clear narration style ideal for reading digital menus or describing daily specials. Her tone remains consistent and easy to understand even in noisy restaurant settings.
- Style: Warm, clear narrator
Friendly Conversational (Milo)
Milo delivers a friendly, conversational tone perfect for welcoming guests or explaining loyalty programs. His approachable voice helps create a welcoming atmosphere without feeling too formal.
- Style: Friendly, conversational
Neutral News (Atlas)
Atlas provides a neutral, news-style delivery suitable for clear instructions or allergen warnings. His straightforward tone ensures important information is conveyed accurately and without emotional bias.
- Style: Neutral, news delivery
Supported Languages
Supporting 23 languages, our TTS API enables restaurant tech startups to serve diverse diners with clear, natural audio. Whether you are broadcasting daily specials or guiding guests through a dining hall, language barriers become a non-issue. Every voice preset handles all supported languages with equal clarity, ensuring consistent quality across your entire operation.
English and Spanish
English remains the default for Latin-script text, but explicit language codes ensure accuracy for other languages. Spanish is fully supported, allowing you to reach bilingual communities with precise pronunciation and natural pacing. This dual capability is essential for menus and notifications in multicultural urban centers.
French and German
French and German are fully supported, providing accurate accent handling and correct stress patterns. This ensures that menu descriptions and allergy warnings sound professional and clear, regardless of the diner's native tongue. The system guesses the language from the script, but setting the language parameter guarantees precision.
23 Languages Total
The platform supports Arabic, Chinese, Danish, Dutch, Finnish, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, and Turkish. Any voice can speak any of these 23 languages. This wide range allows a single API key to power a global restaurant chain or a localized pop-up with equal ease.
- Arabic, Chinese, Danish, Dutch, English, Finnish
- French, German, Greek, Hebrew, Hindi, Italian
- Japanese, Korean, Malay, Norwegian, Polish, Portuguese
- Russian, Spanish, Swahili, Swedish, Turkish
- Vietnamese and Thai are not supported
How It Works
The SavorVoice API follows a straightforward three-step workflow designed for seamless integration into existing restaurant tech stacks. First, you prepare your text content, keeping it under 4,096 characters per request. This limit applies to the entire input, including spaces and punctuation, so menu items or announcement scripts must be concise.
Send Text via API
Construct a JSON payload and send it to the endpoint using POST. You must include your API key in the Authorization header and specify the desired model, voice, and response_format. The system accepts standard ISO language codes to ensure accurate pronunciation, defaulting to English if none is provided for Latin-script text.
- Endpoint:
POST https://api.playak56.com/v1/audio/speech - Supports
tts-1andtts-1-hdmodels - Max 4,096 characters per request
Receive Audio File
Once processed, the API returns the synthesized audio file directly in the response body. The file format matches your requested response_format (mp3, wav, opus, flac, or pcm). Failed requests incur no charge, and the response includes the audio data without storing the generated file for later retrieval.
- Formats: mp3, wav, opus, flac, pcm
- No server-side storage of generated audio
- Immediate response with audio data
Play on Devices
The returned file can be played on digital signage, waiting room speakers, or table notification systems. Since the audio is a standard file, you can stream it using any compatible media player or embed it directly into your existing web or app interfaces without requiring proprietary SDKs.
Pricing Overview
Our pricing is straightforward: $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you only pay for successful audio generation. This character-based model scales naturally with your restaurant’s volume, from simple table notifications to full menu descriptions.
There are no monthly fees or subscriptions. You top up with USDT on the TRON network (minimum $5), and the balance never expires. This eliminates unexpected costs for growing startups needing reliable audio without enterprise complexity.
$0.01 per 1,000 Characters
Each request charges based on the character count of the input text. The rate is consistent regardless of the voice or format selected. Long menus are split into 4,096-character chunks, with audio joined seamlessly.
Failed synthesis returns the full charge, so you never pay for errors. This protects your budget during initial testing phases or when updating daily specials.
- Spaces and punctuation count as characters.
- Failed requests are free.
- No volume discounts needed; linear scaling.
Free Trial Credit
Sign in with Google to receive $0.50 of free credit, valid for 7 days. This allows approximately 50,000 characters of generation, enough to test multiple voices and formats.
Accounts created with email and password do not receive trial credit. This ensures immediate access for teams ready to integrate without waiting for verification.
No Monthly Fees
Usage-based billing means you pay only for what you use. Top-ups are processed automatically within minutes via USDT on the TRON network (TRC-20).
There are no seats, minimum spend requirements, or invoices with VAT. Your balance does not expire, making it ideal for seasonal menu audio or occasional announcement updates.

Technical Integration
The API mirrors the OpenAI speech endpoint structure, allowing you to use official OpenAI SDKs by simply changing the base_url to https://api.playak56.com/v1. This compatibility reduces integration friction for teams already familiar with standard TTS workflows, requiring only a new API key for authentication.
Requests are sent via a standard POST endpoint, accepting JSON bodies with text, voice selection, and format preferences. The system returns an audio file directly in the response, ensuring seamless delivery to your playback devices without complex polling or state management.
OpenAI SDK Compatible
Use existing OpenAI libraries by pointing them to our base URL. Pass your tts-... key in the Authorization header to authenticate requests. This approach leverages proven client implementations, minimizing custom code for your restaurant tech stack.
- Use official OpenAI SDKs with modified
base_url - Standard
Authorization: Bearerheader authentication - Familiar request and response structures
Multiple Audio Formats
Choose from mp3, wav, opus, flac, or pcm based on your playback device’s capabilities. MP3 offers efficient storage for web-based menus, while WAV ensures maximum compatibility with legacy in-house hardware systems.
- mp3 for efficient web delivery
- wav for broad hardware compatibility
- opus and flac for high-quality archival
- pcm for raw audio processing
RESTful Endpoint
Interact with POST https://api.playak56.com/v1/audio/speech using standard HTTP methods. The endpoint accepts text up to 4096 characters, returning the synthesized audio file directly. Metadata like character count and voice used are included for billing transparency.
- Standard
POSTmethod integration - JSON request body structure
- Direct audio file response
Use Cases for Startups
Restaurant tech startups can replace static PA systems with dynamic, API-driven audio that updates in real time. By integrating our TTS endpoint into your ordering or reservation infrastructure, you trigger specific voice clips based on operational events rather than relying on pre-recorded loops.
Indoor Wayfinding
Generate directional audio cues for self-service kiosks or digital signage. Use the neutral Atlas voice for clear instructions like "Checkout is to the left," ensuring consistent guidance without manual recording updates for new locations.
- Triggered by POS events or QR scans
- Seamless MP3 or WAV output for digital displays
- Easy integration with existing restaurant management software
Allergen Announcements
Instantly broadcast ingredient changes or allergen warnings to dining halls. With 23 supported languages, you can serve diverse customer bases using the same API, switching voices like Milos friendly tone for approachable alerts or Sage for instructional clarity.
- Text-to-speech for daily menu changes
- Multi-language support for international menus
- No need for professional voice talent for each update
Loyalty Program Audio
Enhance customer engagement with personalized audio rewards. Send text inputs via the API to generate unique thank-you messages or point notifications, using warm voices like Aria to create a welcoming atmosphere without heavy production costs.
- Voice presets for brand tone
- Character-based pricing keeps costs predictable
- Instant generation via RESTful API endpoints
Why Choose Our API
SavorVoice eliminates billing complexity with a straightforward character-based model. You pay only for what you generate, with no monthly fees or minimum spend requirements. Failed requests are free, ensuring you never pay for errors.
Typical speed is roughly 25 characters per second, generating audio in real-time for long texts. Short phrases take a few seconds, with requests processed sequentially under load.
Your balance never expires, and top-ups via USDT on the TRON network are credited automatically. There are no subscriptions, invoices, or VAT fees, keeping overhead predictable for startup budgets.
Simple Character Billing
Billing is based strictly on character count, including spaces and punctuation. At $0.01 per 1,000 characters, costs remain low even for extensive daily announcements.
- No monthly plans or seat limits
Fast Processing Speed
Typical generation speed is roughly real time, processing about 25 characters per second. This ensures menu updates and notifications are ready for playback with minimal delay.
- Requests processed sequentially
No Hidden Costs
Failed requests incur no charge, with the fee returned in full. There are no hidden subscription fees, VAT invoices, or per-request overheads, making budgeting precise.
Get Started Today
Create your account on the /get-api-key/ page using your Google credentials or email. This simple registration takes seconds and provides immediate access to your personal dashboard without enterprise overhead.
Once registered, you receive a unique API key and $0.50 in trial credit, sufficient for approximately 50,000 characters. This allows you to test audio generation for your menu or notifications immediately.
Sign Up with Google
Visit the sign-up page and select the Google option. Your account is created instantly, linking directly to your balance and usage metrics without requiring a credit card or subscription.
- Instant account creation via Google OAuth
- No credit card required for trial
- Separate accounts per site domain
Get API Key Instantly
Your dashboard displays your active API key immediately after registration. You can view your balance, character usage, and a ready-to-use cURL example to verify connectivity.
The key is active for 60 requests per minute, allowing sufficient throughput for typical restaurant notification volumes. You can issue a new key at any time to invalidate the old one instantly.
- Single active key per account
- Rate limit: 60 requests/minute
- View balance and usage metrics
Start Generating Audio
Use the key with the OpenAI SDK or plain HTTP to send text to the speech endpoint. Receive an audio file in your chosen format (mp3, wav, etc.) and play it on your devices.
With $0.50 trial credit, you can generate roughly 50,000 characters of audio. This covers substantial testing for menu announcements or waiting room background audio before you add funds via USDT.
- Send POST request to /v1/audio/speech
- Receive instant audio file response
- Trial credit: $0.50 (50k chars)
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Your input text is used exclusively to generate the requested audio file and is not retained for model training.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- W3C WAI: making audio and video accessible
- OpenAI API reference: create speech
- Creative Commons Attribution 4.0
- openai-node on GitHub
- MDN: Web Speech API
- LibriTTS-R corpus (OpenSLR 141)
- FFmpeg documentation
- Python documentation
- ISO 639 language codes
- LibriVox public-domain audiobooks
- LibriTTS-R paper (arXiv 2305.18802)
