Hi, I was testing the gemini-2.5-flash-preview-tts model in vertex AI workbench instance but got the error. Other models such as gemini-2.0-flash works fine in the same instance. Any suggestions on how to fix this or any setup needed in GCP?
Error: multi_speaker_voice_config parameter is not supported in Vertex AI
The script used is as follows:
from google import genai
from google.genai import types
import wave
# Set up the wave file to save the output:
def wave_file(filename, pcm, channels=1, rate=24000, sample_width=2):
with wave.open(filename, "wb") as wf:
wf.setnchannels(channels)
wf.setsampwidth(sample_width)
wf.setframerate(rate)
wf.writeframes(pcm)
prompt = """TTS the following conversation between Aaron and Alice as a podcast."""
# genai_client = genai.Client(vertexai=True,
# project=project,
# location=location)
genai_client = genai.Client(vertexai=True, api_key=MY_API_KEY)
response = genai_client.models.generate_content(
model="gemini-2.5-flash-preview-tts",
contents=[prompt, input_json],
config=types.GenerateContentConfig(
response_modalities=["AUDIO"],
speech_config=types.SpeechConfig(
multi_speaker_voice_config=types.MultiSpeakerVoiceConfig(
speaker_voice_configs=[
types.SpeakerVoiceConfig(
speaker='Aaron',
voice_config=types.VoiceConfig(
prebuilt_voice_config=types.PrebuiltVoiceConfig(
voice_name='Kore',
)
)
),
types.SpeakerVoiceConfig(
speaker='Alice',
voice_config=types.VoiceConfig(
prebuilt_voice_config=types.PrebuiltVoiceConfig(
voice_name='Puck',
)
)
),
]
)
)
)
)
data = response.candidates[0].content.parts[0].inline_data.data
file_name='out.wav'
wave_file(file_name, data)
LinkedIn
Twitter
