Joining the hiking club · Training Voiceover 11

Listen first, then inspect the transcript and the request that produced this file.

Listen to the demo

EnglishOne voice0:14

As requestedgemini-3.8-flash-tts · Voice library · Style: bright, upbeat, playful

Human-reviewedFemale voice · Fitting for this scene

Accent notes record one reviewer’s impression. They are not a panel verdict.

Library voice built for en-US (Midwest). Chosen after listening.

Exact transcript

Hey, everyone! I just joined the hiking club this weekend! <laugh> Seriously, I can't wait to see the sunrise from the summit. Bring plenty of snacks, and don't forget comfy shoes. After we head down, let's eat together, my treat!

Generation recipe

This is the request that produced the file. Voice identity and delivery style are separate. Other settings: Default (not sent).

“Copy for AI” (top of this page) copies everything in one Markdown block: the transcript, style, voice, model, the request and example code. “Copy recipe JSON” copies only the raw request.

Show request JSON

{
  "model": "gemini-3.8-flash-tts",
  "input": [
    {
      "type": "user_input",
      "content": [
        {
          "type": "text",
          "text": "Hey, everyone! I just joined the hiking club this weekend! <laugh> Seriously, I can't wait to see the sunrise from the summit. Bring plenty of snacks, and don't forget comfy shoes. After we head down, let's eat together, my treat!",
          "annotations": [
            {
              "type": "speech_metadata",
              "style": "bright, upbeat, playful"
            }
          ]
        }
      ]
    }
  ],
  "response_format": {
    "type": "audio"
  },
  "generation_config": {
    "speech_config": [
      {
        "voice": "en-us-training-11"
      }
    ]
  }
}

Comparison without style

Same transcript, voice and model, with no style direction sent. Listen to both to hear what the style changes.