There seems to have been a change today or yesterday and the transcript quality from nova-3-general is degraded. It is possible that this is also an issue on other models, I didn't check. It seems to consistently return doubled words in the output. This is using the WebSocket STT realtime transcription with PCM 16khz audio with the NodeJS SDK.
e.g. I say 'Tell me why the sky is blue', the transcript I receive is 'Tell tell me why why this sky is blue blue.'
Request ID: dd0797b6-74fa-4f52-a074-69dfd502e3d2