Frequently asked questions
What makes this API best for restaurants?
Q: What makes this API suitable for restaurants? A: It offers simple character-based pricing at $0.01 per 1,000 characters, ideal for menu audio and notifications. The API supports 23 languages and 8 distinct voice presets, enabling clear announcements for dining halls without enterprise complexity or monthly subscriptions.
How does the pricing compare to competitors?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. There are no monthly plans, seats, or minimum spends, making it cost-effective for startups generating audio for menus and drive-thrus.
Are the voices realistic?
Voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. They include eight presets like Aria, Nova, and Felix, providing clear, natural-sounding speech suitable for restaurant menus, notifications, and general announcements.
Do I need to clone voices?
No. Custom voice cloning is not offered. You select from eight preset voices (e.g., Sage for instructional, Felix for promo). Each generated file carries an inaudible watermark marking it as synthetic speech, ensuring authenticity without cloning.
Is there a free trial?
Yes. Signing in with Google provides $0.50 credit (approx. 50,000 characters) valid for 7 days. Email/password accounts start without trial credit. You can top up via USDT on TRON to continue generating audio for your restaurant tech.
How many languages are supported?
Twenty-three languages are supported, including English, Spanish, French, German, Japanese, and Arabic. Any voice can speak any supported language. If the language is not set, it is guessed from the script, defaulting to English for Latin text.
What is the character limit?
Each request accepts up to 4,096 characters. Spaces and punctuation count toward this limit. For longer texts, split the input into parts and join the resulting audio files. Typical speed is roughly real-time on long texts.
Can I use the API for drive-thrus?
Yes. The API generates audio files via a simple POST request. You can integrate it into your drive-thru system to play menu items or announcements. Supported formats include mp3, wav, opus, flac, and pcm for various hardware.
Is the audio watermarked?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This helps identify the content as AI-generated without affecting the listening experience for customers in your restaurant or drive-thru environment.
Do I get a refund for failed requests?
Yes. If synthesis fails, the charge is returned in full. You only pay for successful audio generations. This ensures you are not billed for errors during the creation of menu audio or other restaurant notifications.
How long does top-up take?
Top-ups are credited automatically within minutes after the transfer. Payments are made via USDT on the TRON network (TRC-20) with a minimum of $5. There are no invoices, VAT, or manual processing delays for your balance.
Can I use multiple keys?
Each account has one active key. You can issue a new key at any time, and the old one stops immediately. This allows you to rotate keys for security or manage different environments within your restaurant tech stack.
Is there a rate limit?
Yes, there are 60 requests per minute per key (10 per minute before the first top-up). Requests are processed sequentially, so under load, a request may wait in a queue. Plan your audio generation accordingly.
What formats are supported?
The API supports mp3, wav, opus, flac, and pcm formats. You can specify the format in your request. These formats ensure compatibility with various restaurant audio systems, from web players to hardware speakers in dining halls.
Is the API reliable?
Requests are processed one after another, so under load, a request may wait in a queue. There is no SLA or uptime guarantee. Typical speed is roughly real-time on long texts, but short phrases may take a few seconds.
Do I need a developer?
Yes, a developer is needed to integrate the API. You send a POST request with text and parameters to receive an audio file. The official OpenAI SDKs work by changing the base URL to our API endpoint.
Can I customize the speed?
Yes. You can adjust the speed between 0.25 and 4.0 in your request. This allows you to control the pace of menu announcements or notifications, ensuring clarity for customers in busy restaurant environments or drive-thrus.
Is the data secure?
Input text is used only to produce audio and is not used for training. Generated audio is returned in the response and not stored. Request metadata is kept for billing purposes. There is no on-premise option.
Can I use this for video?
Yes. You can generate audio files (mp3, wav, etc.) and sync them with video content. The API provides audio only, so you handle the video editing separately. This is useful for promotional videos or digital menu boards.
Is there an SLA?
No. There is no SLA, uptime guarantee, or enterprise contract. Support is by email only. There is no phone number or live chat. This lightweight model suits startups without complex enterprise support requirements.
Selection Criteria
Selecting a TTS solution for restaurant tech requires balancing audio clarity with operational cost. For dining startups, every character counts toward the bottom line, making transparent pricing essential. High-quality synthetic voices must sound natural on menu boards and notification systems without sounding robotic.
Cost Efficiency
Character-based pricing at $0.01 per 1,000 characters eliminates unpredictable monthly fees. This model scales linearly with usage, ideal for startups with variable traffic. Failed requests are free, ensuring you only pay for successful audio generation.
- Transparent per-character billing
- No minimum spend or monthly plans
- Free charges for failed requests
Voice Quality
Eight distinct preset voices provide consistent, professional audio for menus and announcements. Voices like Aria and Atlas offer clear, neutral tones suitable for various dining atmospheres. Any voice can speak any of the 23 supported languages, ensuring multilingual menus sound natural.
- 8 licensed preset voices
- Clear narration styles
- Consistent audio quality
Ease of Integration
The API follows the OpenAI endpoint structure, allowing direct use of existing SDKs by changing the base URL. Simple JSON requests and cURL examples reduce development time. RESTful design ensures quick integration into existing restaurant management systems.
- OpenAI SDK compatible
- Simple JSON requests
- RESTful API design
Our API Features
SavorVoice provides a lightweight text-to-speech API designed specifically for restaurant tech startups. Our character-based pricing model ensures you only pay for what you use, eliminating the complexity of enterprise contracts and monthly fees. With a rate of $10 per million characters, you can generate audio for menus and notifications at a predictable cost.
Character-Based Pricing
We charge $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you never pay for errors. Accounts start with a $0.50 free trial valid for 7 days when signing in with Google.
8 Preset Voices
Choose from eight licensed presets based on LibriTTS-R recordings. Female voices include Aria, Nova, Luna, and Sage, while male options are Felix, Milo, Atlas, and Orion. Every generated file carries an inaudible watermark marking it as synthetic speech. Voices are designed for clear narration, upbeat promotions, or calm instructions.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Felix: energetic, promo
- Atlas: neutral, news
OpenAI SDK Compatible
Our API follows the same request shape as the OpenAI speech endpoint. You can use official OpenAI SDKs by simply changing the base_url to https://api.playak56.com/v1. Send a POST request to /v1/audio/speech with your API key. This compatibility allows you to integrate TTS into your existing dining tech stack with minimal code changes.
Voice Comparison
Choosing the right voice affects how customers perceive your brand. SavorVoice offers eight distinct presets, each optimized for specific restaurant contexts. Understanding these differences helps you match audio to your menu’s tone.
Aria vs. Nova
Aria provides a warm, clear narration ideal for menu descriptions. Nova offers a bright, upbeat tone suited for promotional announcements. Both voices can speak any of the 23 supported languages, ensuring consistency across international locations.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat tone
- Both support 23 languages
Milo vs. Felix
Milo delivers a friendly, conversational style perfect for loyalty program updates. Felix brings energetic delivery, making it suitable for time-sensitive promo alerts. Their distinct personalities allow restaurants to segment audio content effectively.
- Milo: Friendly, conversational
- Felix: Energetic, promo-focused
- Distinct personality tones
Atlas vs. Orion
Atlas offers a neutral, news-like voice for clear information delivery. Orion provides a deep, documentary-style tone for premium or historical content. These male presets cover a wide range of informational needs.
- Atlas: Neutral, news-style
- Orion: Deep, documentary-style
- Covers informational needs
Language Support
Serving diverse dining environments requires clear audio across multiple linguistic demographics. Our API supports 23 languages, covering major markets from Arabic to Turkish, ensuring menus and alerts are understood by a broad customer base without needing separate voice providers.
Efficiency matters when generating audio for thousands of menu items. Our system guesses the language from the script, defaulting to English for Latin characters, but allows explicit overrides for precision when handling mixed-script text like Spanish menus in the US.
23 Languages Available
We support Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages, providing flexibility for international restaurant chains or localized pop-ups.
Auto-Detection
When the language field is omitted, the API infers the language from the input script. Latin-script text defaults to English, which suits most standard menu descriptions. This reduces configuration overhead for simple English-only deployments.
Manual Language Set
For non-English Latin-script text, such as French or German menus, you must explicitly set the language parameter. Without this, the system may misinterpret the accent and default to English pronunciation, leading to incorrect audio output for international customers.
Pricing Models
SavorVoice uses a straightforward character-based pricing model, charging $10 per million characters, or $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 structure eliminates hidden fees and scales naturally with your restaurant’s audio needs.
Pay-Per-Use
Our pricing is strictly usage-based. You pay only for the characters processed, with no minimum spend or monthly commitments. This model suits startups with variable traffic, ensuring costs align directly with menu updates or announcement volume.
- Rate: $10 per 1,000,000 characters ($0.01 per 1,000 chars)
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. Your balance does not expire, and you can top up via USDT on the TRON network whenever needed. This removes the administrative overhead of managing recurring invoices or enterprise contracts.
Free Trial
New accounts signing in with Google receive $0.50 in credit, valid for 7 days, allowing for approximately 50,000 characters of generation. Accounts created with email and password start without trial credit, encouraging immediate integration testing without financial risk.
Technical Limits
Restaurant tech requires precise handling of text and request volumes. Understanding these limits ensures your audio notifications and menu announcements play without interruption or delay during peak service hours.
4096 Character Limit
Each API request accepts a maximum of 4096 characters. Since spaces and punctuation count toward this limit, long menu descriptions or detailed waiting alerts must be split into multiple requests. Your application should handle splitting and joining the resulting audio files seamlessly.
60 Requests Per Minute
The API allows 60 requests per minute per key. New accounts start with a lower limit of 10 requests per minute until the first top-up. This rate limit supports steady background operations but may require queuing during high-volume events.
Queue Processing
Requests are processed sequentially. Under heavy load, synthesis may wait in a queue before generating audio. While typical speed is roughly real-time for long texts, short phrases may take a few seconds. Plan your audio triggers to account for this processing time.
Audio Formats
Choosing the right audio format balances playback compatibility with storage efficiency. Our API lets you select the output that best fits your restaurant’s digital infrastructure, ensuring menus and alerts load quickly without compromising clarity.
MP3 Compatibility
MP3 remains the safest choice for widespread device support. It ensures that audio played on digital menu boards, POS systems, and mobile apps works universally across different operating systems and hardware versions.
WAV Quality
WAV provides uncompressed audio. This format is ideal for premium announcements where every nuance of the voice matters, such as detailed dish descriptions or high-end dining notifications, though it consumes more storage.
OPUS Efficiency
OPUS offers compression for smaller file sizes. This is efficient for high-volume usage or slower connections, reducing bandwidth costs while maintaining clear speech for waiting alerts and loyalty notifications.

Integration Ease
Integration requires only a standard HTTP POST to our endpoint. The request structure mirrors the OpenAI speech endpoint, allowing immediate adoption for teams already familiar with modern API patterns.
RESTful API
Send text via POST https://api.playak56.com/v1/audio/speech with a JSON body containing model, input, voice, and response_format. Authentication uses a Bearer token in the header.
Simple cURL
Start instantly with a single command. Replace YOUR_API_KEY and text to receive the audio file directly in your terminal or script output.
- curl -X POST "https://api.playak56.com/v1/audio/speech" \
- -H "Authorization: Bearer YOUR_API_KEY" \
- -H "Content-Type: application/json" \
- -d "{\"model\": \"tts-1\", \"input\": \"Hello\", \"voice\": \"nova\", \"response_format\": \"mp3\"}"
SDK Support
The official OpenAI SDKs work seamlessly by updating the base_url to https://api.playak56.com/v1. Use your existing client code with minimal configuration changes.
Use Case Examples
Restaurants and dining tech startups can leverage our TTS API to automate audio workflows, replacing static sound files with dynamic, text-driven speech. By sending menu updates or queue notifications via a simple POST request, you ensure your audio content stays perfectly synchronized with real-time operations without manual recording.
Menu Boards
Dynamic digital menus benefit from on-demand audio generation. When daily specials change, your system sends the new text to the API, which returns an audio file within seconds. This eliminates the need for recording studio time for every minor menu adjustment, keeping your displays current.
- Update audio instantly when prices or items change
- Use warm voices like Aria for clear readability
- Support multiple languages for diverse customer bases
Waiting Alerts
Queue management systems can trigger audio alerts when a table is ready. By passing the customer’s name or table number into the API, you generate a friendly notification in real-time. This reduces staff intervention and keeps the dining floor organized without constant PA announcements.
- Generate unique notifications for each waiting guest
- Use upbeat voices like Nova to maintain energy
- Integrate directly with existing POS or queue software
Loyalty Audio
Enhance loyalty programs by adding spoken confirmations to point redemptions. When a member scans their code, your backend calls the API to announce their earned points. This personal touch reinforces engagement without requiring expensive custom voice talent or lengthy production cycles for each campaign.
- Announce point balances or rewards instantly
- Maintain brand tone with consistent voice presets
- Scale to thousands of transactions without delay
Data Privacy
Your input text is used exclusively to generate the requested audio file and is not retained for model training. This ensures that your specific menu items or promotional copy remain private and are not repurposed for improving the underlying synthesis engine.
No Training Data
The raw text you send via the API is processed in real-time to produce the audio response. Unlike many competitors, we do not store your input text to train future voice models, keeping your unique restaurant content distinct from our general dataset.
No Audio Storage
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. Once you receive the file, our systems do not retain a copy, ensuring your audio assets belong entirely to your infrastructure.
Billing Metadata
We retain minimal metadata, including the timestamp, character count, and request status, solely for accurate billing and troubleshooting. This data is used only to verify usage against your account balance and does not contain the actual text or audio content.
Support Options
Support for SavorVoice is streamlined to reduce overhead for small teams. We do not offer phone lines or live chat, relying instead on clear documentation and direct email assistance to resolve integration questions efficiently.
Our documentation provides concrete curl examples and SDK usage guides, ensuring you can implement the API without guessing. This approach keeps operational costs low while maintaining reliable access to technical help.
Email Support
All support inquiries are handled via email. This ensures that every question is logged and addressed with specific technical details rather than generic responses. You can expect replies from our team without the wait times associated with phone queues.
For urgent integration issues, email remains the primary channel. We prioritize clarity and accuracy in our responses, helping you troubleshoot API keys, rate limits, or audio format issues directly.
- Direct email access to technical team
- No phone wait times
- Logged and traceable support history
Documentation
Our guides cover the full request lifecycle, from setting up the base URL to handling response formats. We include ready-to-use curl commands and examples for the OpenAI SDKs, making initial integration fast.
The documentation is updated regularly to reflect changes in rate limits or available voices. It serves as the single source of truth for endpoint behaviors, error codes, and character counting rules.
- Ready-to-use curl examples
- Python and JS SDK guides
- Clear error code references
Community
While we do not host a dedicated forum, developers often share integration tips and code snippets in public technical communities. We encourage you to contribute your solutions to help other restaurant tech startups.
This open approach allows us to remain lightweight and focused on core API reliability. You can find relevant discussions by searching for SavorVoice or our API endpoint patterns in developer groups.
- Open developer contributions
- No dedicated forum required
- Collaborative problem solving
Final Recommendation
Cloud TTS API for Restaurant Startups and Dining Tech
Ideal for Startups
SavorVoice delivers reliable synthetic speech without enterprise overhead. With a $0.50 free trial and no minimum spend, dining tech teams can prototype menu audio or loyalty notifications immediately. The simple character-based model scales with your growth, avoiding complex contracts or seat limits.
Built for restaurant workflows, the API handles up to 4096 characters per request with consistent quality. Whether generating English or Spanish menu items, the system ensures clear audio output suitable for digital displays or waiting area speakers.
- No monthly fees or subscriptions
- Free $0.50 trial on Google sign-in
- Supports 23 languages including Spanish and French
Lowest Cost
Pricing is strictly $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests incur no charge, ensuring you only pay for successful audio generation. This transparent model eliminates hidden costs associated with enterprise TTS providers.
Top-ups via USDT (TRC-20) are processed automatically. With no VAT invoices or currency conversion fees, restaurants can manage audio budgets precisely. The low cost makes it viable for high-volume use cases like daily menu updates or promotional announcements.
- $0.01 per 1,000 characters
- Failed requests are free
- USDT (TRC-20) top-ups only
Simple Integration
The API follows the OpenAI speech endpoint structure, allowing immediate use with existing SDKs. By changing the base URL to https://api.playak56.com/v1, developers can integrate voice capabilities into their restaurant tech stack with minimal code changes.
Support for standard formats like MP3, WAV, and OPUS ensures compatibility with most digital signage and audio players. With 60 requests per minute, the system handles routine updates efficiently, while queue processing ensures reliability during peak dining hours.
- OpenAI SDK compatible
- RESTful API with simple cURL examples
- Supports MP3, WAV, OPUS, FLAC, PCM
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
- openai-node on GitHub
- Python documentation
- Creative Commons Attribution 4.0
- openai-python on GitHub
- LibriTTS-R paper (arXiv 2305.18802)
- Node.js documentation
- ISO 639 language codes
- W3C WAI: making audio and video accessible
- OpenAI API reference: create speech
- FFmpeg documentation
- TRON developer hub: TRC-20
