音声設計でカスタム音声を作成する

import base64
import wave

from google import genai

client = genai.Client(enterprise=True, project="PROJECT_ID", location="global")

voice = client.voices.create(
    store=True,
    voice={
        "type": "VOICE_TYPE_PROMPTED",
        "display_name": "Warm British Astronomer",
        "gender": "male",
        "language_code": "en-GB",
        "prompted": {
            "input": (
                "A warm, thoughtful astronomer in his late 60s with a gentle"
                " British accent, speaking with quiet wonder."
            )
        },
    },
    timeout=60,
)

print(f"Created voice ID: {voice.id}")

# Save the voice sample. The SDK returns sample_audio.data as a base64
# string. Raw 16-bit PCM (audio/l16) needs a WAV header.
sample = base64.b64decode(voice.sample_audio.data)
if voice.sample_audio.mime_type.lower().startswith("audio/l16"):
    with wave.open("voice_sample.wav", "wb") as wf:
        wf.setnchannels(1)
        wf.setsampwidth(2)
        wf.setframerate(24000)
        wf.writeframes(sample)
else:
    with open("voice_sample.wav", "wb") as f:
        f.write(sample)

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/voices \
  -d '{
    "store": true,
    "voice": {
      "type": "VOICE_TYPE_PROMPTED",
      "displayName": "Warm British Astronomer",
      "gender": "male",
      "languageCode": "en-GB",
      "prompted": {
        "input": "A warm, thoughtful astronomer in his late 60s with a gentle British accent, speaking with quiet wonder."
      }
    }
  }' > created_voice.json

# Print the voice ID and the encoding of the voice sample.
jq -r '.id, .sample_audio.mime_type' created_voice.json

# Decode the voice sample.
jq -r '.sample_audio.data' created_voice.json | base64 --decode > voice_sample.pcm

from google import genai

client = genai.Client(enterprise=True, project="PROJECT_ID", location="global")

response = client.models.generate_content(
    model="gemini-3.8-flash-tts",
    contents=[{
        "role": "user",
        "parts": [{
            "text": (
                "Look out past the rings of Saturn. Those faint photons left"
                " their source millions of years ago."
            ),
            "speech_metadata": {"style": "reflective and awe-inspired"},
        }],
    }],
    config={
        "response_modalities": ["AUDIO"],
        "speech_config": {"voice_config": {"voice": "VOICE_ID"}},
    },
)

# The SDK has already decoded the base64 audio, so inline_data.data is a
# complete WAV file by default.
with open("designed_voice.wav", "wb") as f:
    f.write(response.candidates[0].content.parts[0].inline_data.data)

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/gemini-3.8-flash-tts:generateContent \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{
        "text": "Look out past the rings of Saturn. Those faint photons left their source millions of years ago.",
        "speechMetadata": {"style": "reflective and awe-inspired"}
      }]
    }],
    "generationConfig": {
      "responseModalities": ["AUDIO"],
      "speechConfig": {
        "voiceConfig": {"voice": "VOICE_ID"}
      }
    }
  }' | jq -r '.candidates[0].content.parts[0].inlineData.data' | base64 --decode > designed_voice.wav

from google import genai

client = genai.Client(enterprise=True, project="PROJECT_ID", location="global")

# List the voices stored in your project.
for voice in client.voices.list(type_=["prompted", "replicated"]).voices or []:
    print(voice.id, voice.display_name, voice.type)

# Get a voice by ID.
voice = client.voices.get(id="VOICE_ID")

# Delete a voice.
client.voices.delete(id="VOICE_ID")

# List the voices stored in your project.
curl -G \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/voices \
  --data-urlencode "type=prompted" \
  --data-urlencode "type=replicated"

# Get a voice by ID.
curl -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/voices/VOICE_ID

# Delete a voice.
curl -X DELETE \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/voices/VOICE_ID