From 98140ca09f41d12b30fc0e78e71a4bd9492038e1 Mon Sep 17 00:00:00 2001 From: 404oops Date: Thu, 15 Oct 2026 09:38:24 +0200 Subject: [PATCH] Clarify Gemini speech instructions --- src/docs/src/AI/txt2speech.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/docs/src/AI/txt2speech.md b/src/docs/src/AI/txt2speech.md index 165f81d29..866be78c0 100755 --- a/src/docs/src/AI/txt2speech.md +++ b/src/docs/src/AI/txt2speech.md @@ -86,7 +86,7 @@ Available when `provider: 'gemini'`: | `voice` | `String` | Voice name. Defaults to `'Kore'`. Available: `'Zephyr'`, `'Puck'`, `'Charon'`, `'Kore'`, `'Fenrir'`, `'Leda'`, `'Orus'`, `'Aoede'`, `'Callirrhoe'`, `'Autonoe'`, `'Enceladus'`, `'Iapetus'`, `'Umbriel'`, `'Algieba'`, `'Despina'`, `'Erinome'`, `'Algenib'`, `'Rasalgethi'`, `'Laomedeia'`, `'Achernar'`, `'Alnilam'`, `'Schedar'`, `'Gacrux'`, `'Pulcherrima'`, `'Achird'`, `'Zubenelgenubi'`, `'Vindemiatrix'`, `'Sadachbia'`, `'Sadaltager'`, `'Sulafat'` | | `instructions` | `String` | Natural language instructions to control speaking style (tone, speed, mood, etc.) | -Gemini reads `text` aloud exactly as written. The `instructions` string is sent to the model as separate style guidance, so it shapes how the text sounds but isn't spoken. Instructions count toward input tokens. Gemini audio is returned as WAV. +Gemini generates speech from the `text` field. The `instructions` string isn't included in the generated audio. It guides delivery (tone, pacing, accent, emotion). Instructions count toward input tokens. Audio is returned as WAV. For more details about Gemini TTS, see the [Google Gemini speech generation documentation](https://ai.google.dev/gemini-api/docs/speech-generation).