Gemini TTS API完全入門：スタイル指定で感情豊かな音声を生成する

# 環境変数に設定
export GEMINI_API_KEY="YOUR_GEMINI_API_KEY"

pip install google-generativeai

import google.generativeai as genai
 
genai.configure(api_key="YOUR_GEMINI_API_KEY")
 
# テキストを音声に変換
response = genai.GenerativeModel(
    model_name="gemini-2.5-flash",
    system_prompt="You are a voice actor with expertise in audio narration."
).generate_content(
    genai.Part.from_data(
        mime_type="text/plain",
        data="Hello, world! This is a test of Gemini TTS."
    )
)
 
# 音声ファイルとして保存
with open("output.mp3", "wb") as f:
    f.write(response.parts[0].inline_data.data)

style_prompt = """
Generate speech for a friendly conversation between friends.
Tone: Warm, approachable, slightly enthusiastic.
Speaking style: Casual, conversational, as if chatting over coffee.
Text: "Hey! I just finished this amazing article about AI.
You've got to check it out when you have time!"
"""
 
response = genai.GenerativeModel("gemini-2.5-flash").generate_content(style_prompt)

style_prompt = """
Generate speech for a professional presentation.
Tone: Confident, authoritative, measured.
Speaking style: Formal yet engaging, with natural pauses.
Text: "Today, we'll explore the fundamental principles of machine learning,
and how they're transforming industries worldwide."
"""

style_prompt = """
Generate speech for dramatic storytelling.
Tone: Emotional, dramatic, engaging.
Speaking style: Expressive, with dynamic energy shifts.
Pacing: Variable - slower for emotional moments, faster for action.
Text: "The sun set over the horizon as she realized everything had changed.
In that moment, she understood what she had to do."
"""

response = genai.GenerativeModel("gemini-2.5-flash").generate_content(
    genai.Part.from_data(
        mime_type="application/json",
        data={
            "text": "Your narration text here",
            "voice_config": {
                "pitch": 0.0,
                "speaking_rate": 1.0,
                "volume_gain_db": 0.0
            }
        }
    )
)

multi_speaker_text = """
Host: Welcome to AI Talk Podcast! Today's guest is an AI researcher.
 
Guest: Thank you for having me! I'm excited to share what we've learned.
 
Host: Let's dive in. What's the biggest misconception about AI?
 
Guest: People often think AI can reason like humans, but...
"""
 
# 話者ごとに別々のAPI呼び出しを実行し、マージする
host_audio = generate_tts(multi_speaker_text, speaker="host", style="warm")
guest_audio = generate_tts(multi_speaker_text, speaker="guest", style="authoritative")
 
# オーディオミキシング
merge_audio(host_audio, guest_audio, output_file="podcast.mp3")