Frequently asked questions
Who runs this site?
SavorVoice operates this independent storefront for the text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. This site provides a lightweight API solution for restaurant tech startups, offering character-based pricing without enterprise complexity or unnecessary overhead.
Are the voices real people?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. They are synthesized audio files generated by our API engine, not live recordings of specific individuals speaking in real-time. Each file carries an inaudible watermark.
Is my text data stored?
Input text is used only to produce the audio and is not stored for other purposes. Request metadata, including time, character count, and status, is kept solely for billing. Generated audio is returned in the response and is not stored on our servers.
Do you use audio for training?
No. Input text is used exclusively to generate the requested audio file. We do not use your input data or generated audio for training our models or improving the engine. Your data remains isolated to your specific synthesis request.
How are voices licensed?
Our voice presets are based on the LibriTTS-R dataset, licensed under CC BY 4.0. The underlying audio samples originate from LibriVox public-domain audiobook readings. This allows us to provide high-quality, legally sound voice options for your restaurant menu and notification audio.
Is there a phone number?
No. We do not have a phone number. Our support structure is designed for efficiency, relying entirely on email communication. This keeps our overhead low and allows us to maintain our simple, character-based pricing model without enterprise complexity.
Do you have live chat?
No. We do not offer live chat support. All customer inquiries are handled via email. This approach ensures that your questions are documented and addressed thoroughly without the pressure of real-time interaction, fitting our lightweight API service model.
Can I claim an SLA?
No. We do not provide a Service Level Agreement (SLA) or uptime guarantee. Our service is designed for startups that value simplicity over enterprise contracts. Requests are processed sequentially, so load may affect speed, but no formal uptime promise is made.
Is the site affiliated with OpenAI?
No. SavorVoice is an independent storefront. Our API endpoint mimics the OpenAI speech endpoint shape, allowing you to use OpenAI SDKs by changing the base URL. However, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand.
How do I contact support?
Support is available via email only. You can reach us through the contact page or by emailing our support team. We do not offer phone support or live chat. Please include your API key and details of your issue for faster resolution.
What is the editorial team?
This site is an independent storefront. The content reflects the factual capabilities of our text-to-speech API, written to help restaurant tech startups understand the technical details and pricing of our service.
Do you sell other products?
No. This site sells only our text-to-speech API. We do not offer speech-to-text, translation, dubbing pipelines, or video editing tools. We also do not have WordPress plugins, browser extensions, or mobile SDKs. Our focus is strictly on audio generation.
Is the data secure?
Input text is used only for synthesis and not stored. Request metadata is kept for billing. We do not offer specific certifications like SOC 2, HIPAA, or GDPR certificates, nor do we provide on-premise installation options. Data handling is standard for our API.
Can I use the voices commercially?
Yes. The voices are based on CC BY 4.0 and public-domain sources. You can use the generated audio for commercial purposes, such as restaurant menus, notifications, and announcements. Each file includes an inaudible watermark to identify it as synthetic speech.
Are the voices watermarked?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This helps identify the audio as AI-generated without affecting the listening experience. The watermark is embedded directly into the audio file during synthesis.
Do you have a privacy policy?
We do not explicitly list a separate privacy policy document, but our data practices are defined by our product facts. Input text is not stored or used for training. Metadata is kept for billing. Generated audio is not stored. Contact us via email for details.
Is the team remote?
Support is handled via email, and our API is cloud-based. The team operates remotely to maintain a lightweight, low-overhead service model.
Do you accept feedback?
Yes. You can send feedback or support inquiries via email. We do not have live chat or phone support. Your feedback helps us maintain our lightweight API service. Please contact us through the official channels provided on our site for any suggestions.
Is the site global?
Yes. Our API supports 23 languages, including English, Spanish, French, German, Chinese, Japanese, and others. The service is accessible globally via our cloud endpoint. We do not restrict usage by region, and our pricing is consistent regardless of your location.
Do you have offices?
No specific office locations are listed. We operate as a cloud-based API service with no physical storefronts or listed offices. Our support is remote, handled via email. This structure allows us to offer a lightweight API without the overhead of physical locations.
Our Mission
SavorVoice is an independent storefront for a text-to-speech API. We strip away marketing hype to focus on what actually matters for your menu audio, notifications, and announcements: reliability, clear pricing, and ease of integration.
Simplify Audio Tech
We evaluate technical specifics like character limits, voice presets, and response formats without assuming you need enterprise-grade complexity. Our goal is to help you find the exact tool that fits your current stack, whether you are building a digital menu board or an order confirmation system.
Support Startups
Startups need predictable costs and straightforward integrations. We highlight how SavorVoice handles character-based billing and simple SDK usage, allowing your small engineering team to deploy audio features without negotiating custom contracts or managing complex infrastructure.
Transparent Pricing
We break down costs clearly, showing exactly what you pay per million characters and what features are excluded. Our reviews always compare the actual price against the delivered quality, ensuring you know the total cost of voice generation before you commit to a provider.
Editorial Team
We document the JSON request bodies, including model selection between 'tts-1' and 'tts-1-hd'.
We understand the specific needs of restaurant tech, such as quick notification audio and clear menu descriptions.
Expert Reviewers
Our reviewers analyze the API’s performance under load, verifying that character-based pricing holds steady at $0.01 per 1,000 characters. They test the 60 requests-per-minute limit to ensure reliable delivery for high-volume menu broadcasts without unexpected delays.
Technical Writers
Technical writers document the JSON request bodies, including model selection between 'tts-1' and 'tts-1-hd'. They explain the OpenAI SDK compatibility, detailing how to swap the base_url for seamless integration into existing restaurant management systems.
Industry Specialists
Industry specialists focus on the specific constraints of dining environments. We understand the specific needs of restaurant tech, such as quick notification audio and clear menu descriptions, ensuring voices like Felix or Aria remain intelligible in noisy settings.
Voice Licensing
Our voices are rooted in licensed recordings, ensuring legal clarity for commercial use. We rely on established open-source datasets to deliver audio.
This approach guarantees that every generated file is built on verified, pre-existing human performances rather than opaque black-box algorithms.
LibriTTS-R Source
All eight voice presets are derived from the LibriTTS-R dataset. This provides a consistent baseline for voice quality and tonal characteristics across all models.
The dataset was carefully curated to ensure clarity and suitability for text-to-speech applications, maintaining a professional standard for restaurant notifications and menu announcements.
- Based on the LibriTTS-R dataset
- Used for all 8 voice presets
- Ensures consistent audio quality
CC BY 4.0 License
The underlying data is licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This allows us to legally process and synthesize the audio while respecting the original creators' rights.
You receive the audio output without needing to manage individual voice licenses, simplifying your compliance workflow.
- CC BY 4.0 licensed data
- Simplified compliance for users
- Legal clarity for commercial use
LibriVox Recordings
The audio samples originate from LibriVox, a platform of public-domain audiobook readings. These recordings offer natural prosody and authentic human intonation.
By using these established recordings, we ensure that the synthetic speech sounds natural and engaging, suitable for engaging diners with menu items or special offers.
- Source: LibriVox public-domain readings
- Natural prosody and intonation
- Authentic human performance basis
Data Policy
SavorVoice processes text exclusively to generate audio files for immediate delivery. The input text is not retained for model training or fine-tuning. Generated audio is returned in the response and is not stored on our servers after delivery.
No Text Training
We do not use your input text to train or improve our TTS models. Each request is processed in isolation to produce the requested audio file.
No Audio Storage
Generated audio files are returned directly in the API response and are not stored on our servers. This ensures that your menu audio or announcements are not kept longer than necessary for the request lifecycle.
Billing Metadata Only
We retain request metadata, including timestamp, character count, and status, solely for accurate billing and troubleshooting. No audio content or source text is kept for analysis.

Honest Limits
SavorVoice delivers a lightweight, character-based API designed for restaurant tech startups that need reliable audio for menus and notifications. We prioritize simplicity and transparent pricing over enterprise complexity, ensuring you only pay for what you use without hidden fees or minimum spends.
Our editorial team provides honest technical details, reviewing the product’s actual capabilities against real-world workflows. We avoid hype, focusing on concrete facts like the 60 requests per minute rate limit and the specific voice presets available for different dining scenarios.
No Streaming
The API returns a complete audio file after processing, rather than streaming partial chunks in real-time. This means there is no WebSocket connection for live audio playback. For menu announcements or pre-recorded notifications, this batch processing is sufficient and often more reliable than maintaining a persistent stream.
Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time on long texts, but short phrases may take a few seconds to generate.
- Complete file return, no real-time chunks
- Sequential processing under load
- Suitable for pre-recorded notifications
No Custom Cloning
We do not offer custom voice cloning or the ability to upload your own voice recordings. You choose from eight preset voices, such as Aria for warm narration or Felix for energetic promos, all based on licensed recordings from LibriTTS-R and LibriVox.
Our model uses fixed presets. This keeps the API lightweight and ensures consistent quality across all generated audio files, which also carry an inaudible synthetic watermark.
- 8 fixed presets only
- No user-uploaded voice samples
- Based on LibriTTS-R & LibriVox
No SLA
We do not provide an official Service Level Agreement (SLA) or uptime guarantee. As a lightweight API for startups, we avoid enterprise contracts and certifications like SOC 2 or HIPAA. This keeps our pricing simple and affordable.
Support is available via email only, with no phone number or live chat. If synthesis fails, the charge is returned in full, but there is no guaranteed response time or financial penalty for downtime.
- No uptime guarantee
- No enterprise contracts
- Email support only
Contact Us
Our editorial team and technical writers maintain this site to provide honest, figure-driven reviews of TTS technology for restaurant startups. We focus on clear, verifiable facts rather than marketing hype, ensuring you know exactly what you are integrating into your digital menus and announcements.
Email Support
All inquiries regarding billing, API keys, or technical issues are handled via email. This allows our team to provide detailed, documented responses without the pressure of real-time availability, ensuring accurate solutions for your integration needs.
- Response time varies based on volume.
- No guaranteed SLA for support tickets.
- Primary channel for all account issues.
No Phone Number
We do not maintain a public phone line. This keeps our operational overhead low, allowing us to pass savings on to you through our simple character-based pricing model. You can reach us directly through the email channels listed above.
No Live Chat
Unlike many SaaS platforms, we do not offer live chat widgets. This reduces latency and distraction for our editorial and engineering teams, allowing them to focus on maintaining the API stability and accuracy of our voice models for your restaurant tech stack.
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.
