What multilingual TTS means
KORENANI has verified implementation for text-to-speech and generated audio. The iOS side uses speech synthesis, and backend services generate audio for labels and details on recognized objects. Fact refs: docs/seo/02-facts.md:130-138.
Verified languages
The verified language and TTS records include Japanese, English, Spanish, French, German, Italian, Portuguese, Chinese, and Korean language codes or resources. Fact refs: docs/seo/02-facts.md:115-129.
Label and detail audio
The backend TTS generation service generates audio for labels and metadata, then uploads audio paths connected to recognized objects. Fact refs: docs/seo/02-facts.md:136-138.
Pairing audio with photo learning
Photo-based object recognition can support family conversation when the label can be seen and heard. The iOS permission text connects camera, photo library, and microphone use with educational object recognition, learning, and custom pronunciations. Fact refs: docs/seo/02-facts.md:177-179.
Next guides
For recognition details, read General, Insect, and Plant Recognition Modes. For data handling, read How Photo Data Flows During Image Recognition.