Frequently asked questions
Who owns the voices used in the API?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We provide access to these eight preset voices—such as Aria, Nova, and Felix—via our API endpoint without requiring separate licensing for the underlying source material.
Are the voices based on real human recordings?
Yes. Every voice preset is derived from licensed recordings and public-domain audiobook readings. Each generated audio file contains an inaudible watermark that explicitly marks the output as synthetic speech.
Is the API affiliated with OpenAI?
No. We are an independent storefront for a distinct text-to-speech API. Our endpoint structure mimics the OpenAI speech endpoint for SDK compatibility, but we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons.
Do you have an office in the US?
We do not maintain physical offices or provide phone support. Our operations are fully cloud-based, and support is handled exclusively via email. There is no on-premise installation option or data-center choice available, as the service is entirely remote.
Can I get a refund if I don't like the voices?
Failed requests receive a full charge return. However, successful generations are consumed as billed. There are no subscriptions or minimum spends, so you can simply stop using the API. We do not offer refunds for successfully processed audio files.
Do you offer custom voice design?
No. We offer eight fixed presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). We do not provide custom voice cloning, emotion tags, or the ability to upload your own voice. You must choose from the available library of eight voices.
Is the API SOC 2 certified?
No. We do not provide an SLA, uptime guarantee, or enterprise contracts. We also do not hold certifications such as SOC 2, HIPAA, or GDPR certificates. Our service is designed for straightforward, character-based billing without enterprise compliance overhead.
Do you store my API key securely?
You receive one active key per account, which can be revoked instantly to issue a new one. We keep request metadata (time, characters, status) for billing purposes. Input text is used only to produce audio and is not stored for training.
Can I use the API for commercial purposes?
Yes. There are no monthly plans, seats, or minimum spends. You pay $0.01 per 1,000 characters. Generated audio is returned in the response and not stored by us, allowing you to use the output for your commercial transport announcements.
Do you have a mobile app?
No. We do not offer a mobile SDK or a dedicated mobile application. You can use the official OpenAI SDKs by changing the base URL, or use plain HTTP requests from any device capable of making API calls.
Is the API available in other countries?
Yes. The API is cloud-based and accessible globally. We support 23 languages including English, Spanish, German, French, and others. You can specify the language via an ISO code or let the system guess it from the text script.
Do you offer discounts for non-profits?
No. We offer a flat rate of $10 per million characters with no tiered pricing or discounts for specific sectors like non-profits. There are no subscriptions or volume discounts; you pay only for the characters you generate.
Can I use the API for emergency announcements?
Yes. The API supports text up to 4,096 characters per request. You can split longer texts into parts and join the audio files. This allows you to deploy clear, multilingual announcements for transport teams without relying on human operators.
Is the API secure for passenger 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 for billing. However, we do not offer specific certifications like HIPAA.
Can I integrate the API with my existing transport software?
Yes. The endpoint matches the OpenAI speech endpoint shape. You can use the official OpenAI SDKs by changing the base URL to https://api.paisita.info/v1. This allows easy integration with existing software stacks.
Do you offer technical support for API integration?
We offer support via email only. There is no phone number, live chat, or dedicated technical account manager. Documentation is available at /docs/, and you can use standard HTTP requests or OpenAI SDKs for integration.
Can I use the API for multilingual announcements?
Yes. We support 23 languages including 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.
Who we are
Paisita Voices operates as an independent cloud API provider, delivering text-to-speech synthesis directly to transport teams without intermediary layers. Our infrastructure is built to handle high-volume announcement generation for mixed-language regions, ensuring consistent audio output across diverse fleets.
We focus exclusively on the logistics and transport sector, designing our system to simplify deployment for large teams requiring reliable, character-based audio updates. By removing enterprise contract overhead, we provide a straightforward path to multilingual public address systems.
Independent API provider
We are not affiliated with major tech brands or voice cloning studios. Our API endpoint (https://api.paisita.info/v1) serves requests directly, compatible with standard HTTP clients and OpenAI SDKs, allowing transport IT teams to integrate quickly.
Focused on transport sector
Our engine is optimized for clear, intelligible announcements suitable for bus, train, and truck fleets. With support for 23 languages, we enable consistent communication in regions with diverse passenger demographics, handling up to 4096 characters per request for detailed route instructions.
No corporate overhead
Unlike enterprise vendors, we offer no minimum spend, no seats, and no monthly plans. You pay only for what you use ($0.01 per 1,000 characters), with a simple USDT top-up system. This model suits large teams that need flexibility without long-term commitments.
Voice licensing
Our voices are derived from licensed recordings, ensuring transparent legal foundations for commercial transport announcements. We utilize the LibriTTS-R dataset under a Creative Commons Attribution 4.0 International License, providing clear usage rights for generated audio files.
The underlying audio samples originate from LibriVox public-domain audiobook readings, allowing reliable voice synthesis without complex royalty tracking. This licensing structure supports large transport teams deploying consistent multilingual updates across mixed-language regions.
LibriTTS-R license (CC BY 4.0)
The LibriTTS-R dataset is distributed under the CC BY 4.0 license, which permits commercial use with attribution. This standard license covers the synthetic voice models generated by our API, ensuring that transport operators can use the audio in internal communications and public announcements.
- Permits commercial use
- Requires attribution
- Standard CC BY 4.0 terms
LibriVox public-domain recordings
The foundational voice data comes from LibriVox, which curates public-domain audiobook readings. These recordings serve as the source material for our eight voice presets, combining clear narration with the stability needed for repetitive transport announcements.
Clear usage rights
Each generated file carries an inaudible watermark marking it as synthetic speech, aiding in content verification. You retain full rights to the generated audio for your operational needs, with no ongoing royalties per character or request.
Data privacy policy
We process input text exclusively to generate the requested audio file. The content you submit is not ingested into our training datasets, ensuring that your specific transport announcements and route data remain distinct from the models used to synthesize other voices.
Input text not used for training
Your text is used only for the immediate synthesis task. We do not retain your specific scripts to improve our core voice models, preserving the confidentiality of your operational data.
No long-term audio storage
Generated audio is returned directly in the API response and is not stored on our servers after delivery. This minimizes exposure of your broadcast content.
Metadata kept for billing
We retain request metadata, including timestamp, character count, and status, solely for billing and usage tracking. This data is kept only as long as necessary to process your account.
Technical limitations
The API returns complete audio files rather than streaming partial chunks. Requests are processed sequentially, meaning under load a request may wait in a queue. Short phrases take a few seconds to generate, while longer texts synthesize at roughly real-time speed (25 characters per second).
No streaming or WebSocket
We do not offer real-time audio streaming or WebSocket connections. Clients must wait for the full audio file to be generated and returned in the response. This synchronous model ensures consistency but requires handling potential queue delays during high demand.
No SSML support
The endpoint accepts plain text only. There is no support for SSML, phoneme dictionaries, or custom pronunciation lexicons. You cannot control intonation, pauses, or emphasis via markup. For mixed-language regions, set the language field explicitly to ensure correct pronunciation.
No custom voice cloning
We do not offer custom voice cloning for customers. You cannot upload your own voice recordings to create a new voice profile. The system provides eight fixed presets based on licensed recordings. If you need a specific voice not among the eight options, it is not available.

Support and contact
Paisita Voices operates as an independent API provider for the transport sector, focusing on reliable text-to-speech delivery without corporate overhead. We understand that logistics teams require consistent, multilingual announcements for mixed-language regions, and our system is designed to simplify that deployment.
Email-only support
Our support team handles all inquiries via email. This allows for detailed technical troubleshooting and clear documentation of your account status, rate limits, and billing questions without the noise of phone queues.
- Response time: Typically within one business day.
- Support for API key issuance and balance inquiries.
- Detailed technical assistance for integration issues.
No phone number
We do not maintain a dedicated phone line. This decision keeps our operational costs low, allowing us to offer competitive pricing ($0.01 per 1,000 characters) without the overhead of a call center. All communication is asynchronous and documented.
- No voice support line.
- All interactions recorded via email for audit trails.
No live chat
Unlike some consumer-focused platforms, we do not offer live chat widgets. This ensures that support agents can focus on complex integration questions rather than handling multiple simultaneous casual queries. You can reach us directly at [email protected].
- No real-time chat widget on the website.
- Direct email access for all support needs.
Company history
Paisita Voices was established to remove the administrative friction from deploying multilingual text-to-speech systems. Large transport teams often require consistent audio updates across mixed-language regions without the overhead of enterprise contracts or complex licensing structures.
Our growth in the transport sector stems from providing a reliable, character-based API that simplifies deployment. We focus on delivering clear, synthetic announcements for logistics teams, ensuring consistency without the need for custom voice design or extensive infrastructure management.
Founded to simplify TTS
We built this API to solve a specific problem: the high cost and complexity of securing multilingual announcement systems for large fleets. By standardizing on a single API endpoint, we eliminated the need for disparate voice providers and reduced integration time for logistics software.
Growth in transport sector
We prioritize consistent audio quality and straightforward billing, allowing teams to scale their audio updates without managing multiple vendor contracts or dealing with unpredictable enterprise overhead.
Future roadmap
We continue to refine our API to support larger transport teams and more complex multilingual workflows. Our focus remains on reliability and simplicity, ensuring that our infrastructure scales efficiently as your fleet grows, without introducing unnecessary features or complex licensing models.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Her voice remains engaging without fatigue, making her suitable for comprehensive journey updates.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- ISO 639 language codes
- MDN: Web Speech API
- LibriTTS-R paper (arXiv 2305.18802)
- openai-node on GitHub
- curl documentation
- LibriVox public-domain audiobooks
- TRON developer hub: TRC-20
- Node.js documentation
- IETF RFC 7845: Ogg Opus
- LibriTTS-R corpus (OpenSLR 141)
- W3C WAI: making audio and video accessible
