# Lovora Research: Measurements From Running an AI Companion Service > Research notes published by Lovora from its own production data: AI moderation false-positive rates, multilingual text-to-speech quality measured by word… Source: https://lovora.ai/research [← Lovora](https://lovora.ai/) Last updated: September 27, 2026  |  Lovora is an adults-only (18+) service on which all content is generated by artificial intelligence. Lovora is an adults-only AI companion service used in nine languages. Running it produces measurements that are hard to find elsewhere — how moderation models behave on explicit content, how open speech models perform outside English and Chinese, which engineering defects only appear in a multilingual product. We publish them here. Every note states its method, sample size and limitations, and is free to quote or republish under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) with a link to the source. Press and data requests: [info@lovora.ai](mailto:info@lovora.ai); see also the [press page](https://lovora.ai/press). ## 1. Research notes - [AI girlfriend statistics 2026: what 1,533 first conversations show](https://lovora.ai/research/ai-girlfriend-usage-statistics) (September 2026). Countries (81% outside the English-speaking world), devices, ready-made vs self-designed companions, what people ask for, and how online age checks end — 30 days of production data. - [When the model that writes erotica also moderates it: 83–92% of blocks were wrong](https://lovora.ai/research/moderation-false-positives) (September 2026). Three audits re-judging every historical AI moderation block by hand (35 and 93 blocks); why a roleplay model makes a poor judge; the two-pass design that replaced it; four ways false positives were turning into suspensions. - [CosyVoice2 vs Chatterbox Multilingual in production: word error rate in eight languages](https://lovora.ai/research/multilingual-tts-benchmark) (September 2026). Round-trip WER per language, GPU memory, real-time factor and latency on a shared 22.5 GB GPU; proof that a larger Whisper model does not fix bad audio; deployment pitfalls. - [JavaScript’s \b is ASCII-only: how it silently disabled rules in six languages](https://lovora.ai/research/unicode-word-boundaries) (September 2026). Three production incidents from one defect, the Unicode-aware replacement, and a script that finds the bug in any codebase. ## 2. How these notes are written - **Measured, not estimated.** A figure appears only if it was measured on the production system or on a documented test set. - **Failures included.** Most of these notes exist because something was wrong. They say so, with the numbers from before the fix. - **Nothing that helps abuse.** Moderation prompts, detection patterns and known gaps are described in general terms only. - **No personal data.** Examples from user traffic are paraphrased or reduced to the words needed to show the finding. ## 3. Related reference documents The current state of the service, as opposed to how it got there, is described in the reference documents: [Safety, Moderation and Enforcement](https://lovora.ai/safety), [Languages, measured](https://lovora.ai/languages), [Voice notes and calls](https://lovora.ai/voice-and-calls) and [How Lovora works](https://lovora.ai/how-it-works). ## 4. Questions people ask ### What does Lovora publish research about? Things it has measured while running its own service: how often AI moderation blocks the wrong content, how well open text-to-speech models work in different languages, and engineering defects that affect multilingual software. ### Can Lovora research be quoted or republished? Yes. Every research note is published under Creative Commons Attribution 4.0: it may be quoted or republished, including commercially, with a link to the note as the source. ### Where does the data come from? From Lovora's own production systems and logs. Each note states its method, sample size and limitations. No personal data is published; examples are paraphrased or reduced to the minimum needed to show the finding. ## Related documents - [Press and media](https://lovora.ai/press) - [Safety, moderation and enforcement](https://lovora.ai/safety) - [Languages on Lovora, measured](https://lovora.ai/languages)