Frequently asked questions
Who runs Voisite?
Voisite is an independent storefront for a cloud text-to-speech API. We operate as a standalone service, providing reliable synthetic narration for audioguides and video tours without being part of a larger tech conglomerate.
Are we affiliated with OpenAI?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our API endpoint mimics the OpenAI speech endpoint shape, so existing OpenAI SDKs work by simply changing the base_url, but we are a separate entity.
Where do the voices come from?
Our eight voice presets 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 marking it as synthetic speech, ensuring clear attribution to our specific synthetic generation process.
Do you sell user data?
Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata (time, characters, status) solely for billing purposes, ensuring your creative content remains private.
How do I contact support?
Support is available by email only. We do not offer phone support, live chat, or a dedicated phone number. For inquiries regarding your account, billing, or technical issues, please reach out via the contact form on our /contact/ page.
Is there a phone number?
No, there is no phone number for Voisite. All customer support is handled exclusively through email. This allows us to maintain a lean, independent operation focused on delivering a reliable API for tourism and museum audio content without overhead costs.
Do you have an office?
We do not list a physical office address. As an independent API service provider, our operations are cloud-based. You can manage your account, view usage, and retrieve your API key directly through our web interface at /get-api-key/.
Can I request a new voice?
We do not offer custom voice cloning or voice design. You can choose from eight existing presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). If you need a specific tone, you can select the closest match from our current library.
How is the license verified?
We use voices sourced from LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. Each generated audio file contains an inaudible watermark that marks it as synthetic speech. This watermark helps verify that the audio was generated by our API service.
Do you store audio files?
Generated audio is returned in the response and is not stored by us. Input text is used only for synthesis and is not used for training. We retain request metadata, such as timestamp, character count, and status, strictly for billing accuracy.
Can I use the voices commercially?
Yes. Our voices are based on licensed recordings and public-domain sources, making them suitable for commercial use in tourism, museums, and audioguides. You can scale your audio content from video tours to professional narration.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. We do not offer manual refunds for successful generations. Your balance does not expire, and you can top up via USDT (TRC-20) whenever needed.
Is the API open source?
No, we do not offer an official SDK of our own, nor is the API code open source. You can use the official OpenAI SDKs by changing the base_url to https://api.play2288.com/v1, or use plain HTTP requests to interact with our endpoints.
How do you handle disputes?
We handle disputes via email support. We maintain request metadata for billing disputes, ensuring transparency regarding characters used and charges incurred.
Our Mission
Voisite exists to democratize professional narration for tourism and museum projects. We provide a reliable text-to-speech API that allows agencies to generate consistent, high-quality audio guides without the logistical overhead of hiring voice talent for every new tour. By simplifying the production pipeline, we enable teams to scale their audio content efficiently.
Democratizing Narration
Our goal is to make studio-quality narration accessible to any organization, regardless of size. We strip away the complexity of audio production, allowing you to focus on content rather than recording logistics. With straightforward pricing and a simple API, you can produce dozens of audio guides from a single source text.
Supporting Tourism Agencies
We designed our workflow specifically for the needs of tourism agencies and museum guides. Whether you are creating audioguides for historic sites or video tours for travel brochures, our API delivers clear speech in 23 languages. This ensures your visitors receive a consistent experience across all your locations, from short phrases to full-length tours.
- Consistent voice identity across multiple locations
- Scalable production for large content libraries
- Support for diverse languages and dialects
Independent Focus
As an independent service, we are not tied to the specific business models of major tech giants. This allows us to remain focused on the specific needs of the tourism industry. We prioritize reliability and clear communication, ensuring that our API integrates seamlessly into your existing content management and distribution workflows without unnecessary bloat.
Voice Licensing and Sources
Voisite’s synthetic voices are built on licensed recordings from the LibriTTS-R dataset, ensuring legal clarity for tourism and museum audio projects. This foundation allows agencies to scale narration without complex rights management.
Our voices are derived from LibriVox public-domain audiobook readings, providing a vast library of clear, high-quality speech patterns that form the basis of our eight distinct voice presets.
LibriTTS-R License
We utilize the LibriTTS-R dataset, which offers a robust collection of speech data. This license supports reliable commercial use, allowing tourism agencies to integrate TTS into audioguides and video tours.
- High-quality dataset for voice training
- Supports consistent narration quality
CC BY 4.0 Compliance
All source material adheres to the Creative Commons Attribution 4.0 International license. This ensures that the underlying voice models are legally sound for generating synthetic speech for client projects.
- Clear attribution standards
- Commercially friendly license terms
Public Domain Readings
The voices are based on recordings from LibriVox, which provides public-domain audiobook readings. These readings serve as the raw material for our eight voice presets, from the warm narrator 'Aria' to the deep documentary voice 'Orion'.
- Source: LibriVox public domain
- Basis for all 8 voice presets
Data Privacy and Usage
When you send text for narration, we process it solely to generate the audio file. Your input is not retained after synthesis completes, ensuring that your script content remains private and secure during the creation process.
Input Text Usage
Your text is used exclusively to produce the requested audio format. We do not store the text after the audio is generated and returned to you.
Audio Storage Policy
Generated audio is returned directly in the API response and is not stored on our servers. You maintain full ownership of the resulting files, which you can save, distribute, or integrate into your audioguide apps immediately.
No Training on Data
We do not use your input text or generated audio for model training. Your unique voiceovers remain distinct from our general dataset, preserving the originality of your museum and tourism content without contributing to other models.
Our Editorial Team
Voisite is an independent storefront for a cloud text-to-speech API.
We focus on delivering consistent, high-quality narration that scales easily from audioguides to video tours without the overhead of hiring voice talent for every project.
Who We Are
Expertise in Tourism
Our team has extensive experience in tourism and museum contexts, ensuring our voice presets like 'sage' for instructional content and 'aria' for narrators fit naturally into guided experiences.
Technical Background
With a strong technical foundation, we maintain the API infrastructure that processes up to 4096 characters per request, ensuring reliable delivery of audio files for your tours.

Contact and Support
We prioritize clear, documented communication for tourism and museum teams managing complex audio workflows. Our support is designed to help you integrate the API smoothly, from initial setup to troubleshooting generation issues.
All inquiries are handled via email.
Email Support
Send your questions to [email protected]. Whether you need help with voice selection, rate limits, or billing, our team is ready to assist.
- Single point of contact for all technical and billing queries.
- Detailed responses that can be saved for future reference.
No Live Chat
We do not offer live chat or phone support. This allows us to maintain a focused, asynchronous workflow that doesn't disrupt our development and maintenance cycles.
Response Times
During peak tourism seasons, response times may vary slightly depending on inquiry volume.
- Business days only.
- No 24/7 guaranteed availability.
Technical Limitations
Our API prioritizes reliable, batch-generated audio over real-time interactivity, making it ideal for pre-produced museum guides and tourism videos rather than live conversational applications. We do not offer streaming or WebSocket connections; clients receive the complete audio file once synthesis finishes. This approach ensures consistent quality and predictable delivery for your audio content pipelines.
No Streaming
Unlike live voice assistants, our service returns the full audio file after processing. You cannot receive partial audio chunks in real time. This means you must wait for the entire request to complete before playing the audio, which suits pre-recorded tours but not instant conversational interfaces.
No Custom Cloning
We provide eight preset voices derived from licensed recordings, but we do not offer custom voice cloning. You cannot upload a reference audio file to create a unique voice for your brand. Each generated file includes an inaudible watermark to identify it as synthetic speech.
Rate Limits
Your API key is limited to 60 requests per minute, or 10 per minute before your first top-up. Requests are processed sequentially, so under heavy load, synthesis may queue. Longer texts are split internally, but each chunk counts toward your limit. Failed requests do not consume your quota.
- 60 requests/minute per key (10 before top-up)
- Sequential processing may cause brief delays
- Failed requests are free and do not affect limits
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.
