https://ai.google.dev/gemini-api/docs/music-generation#output-format
All I want is for a Lyira 3.5 API call to return a WAV. It’s only returning MP3s, even though your documentation, for whatever reason, says WAV file.
Your docs say:
By default, the Lyria 3.5 models generate audio in MP3 format. For Lyria 3.5, you can also request the output in WAV format by setting the response_format.
Python:
interaction = client.interactions.create(
model=“lyria-3.5”,
input=“A beautiful piano melody.”,
response_format={“type”: “audio”},
)
output_audio.mime_type is audio/mpeg, and the base64 starts with SUQz, which decodes to ID3, the MP3 tag header.
Did you guys just mark it wrong in your documentation, and this feature doesn’t exist yet? Someone help, please.