TTS (text-to-speech)
Japanese TTS（音声合成）
TTS (text-to-speech) is technology that turns written text into spoken audio that sounds like a human voice. It lets you make announcements or video narration without recording, but supported languages and usage terms differ from tool to tool.
TTS (text-to-speech) takes written sentences and has a computer read them aloud in a chosen voice, producing an audio file. It is a bit like a player piano that plays by itself once you feed it sheet music. Google Cloud's documentation calls the step of turning text into audio data "synthesis" and returns the result as a file such as MP3. You can pick voices by language, gender, and accent.
Watch out First check that the model you want supports your language. For example, the model page for Parler-TTS Mini v1 lists it as English only. If you plan to use the audio in a shop video or on your website, read the usage terms too: ElevenLabs says commercial usage rights come only with paid plans. If numbers or abbreviations are read oddly, a markup standard called SSML lets you adjust the pronunciation.
Source: Google Cloud documentation; ElevenLabs documentation; Hugging Face Parler-TTS model page; W3C SSML