Mark Backman

Was subsequent audio transcribed by Deepgram after the `finalize failed` message? That is, was only that one audio sample not transcribed and subsequent chunks were transcribed?

> We also see InterimTranscriptFrames that aren't followed by a TranscriptFrame. This is a possible scenario with Deepgram. If a final transcript wasn't provided, my understanding is that the confidence...

There was a regression in 0.0.74 when we updated the resampler. This is causing resampling to not work correctly for Telephony providers (and possibly other cases). We're going to look...

@obigroup the best practice is to set the `audio_in_sample_rate` and `audio_out_sample_rate` in the `PipelineParams`. Why does this work? These sample rates are passed to the `StartFrame`, then upon initialization, every...

> I was using an unsupported language for nova-3. > > Consider improving the integration error reporting. Deepgram's `connection.start()` returns `False` on failure, but doesn't provide error details, so there's...

This is a known weakness in Pipecat. The bot's speaking state is based on a VAD-like heuristic. We have plans to improve how this works. @aconchillo has this on his...

There is a WIP branch that @aconchillo has but he's been busy working on other things. You can see this response for guidance to avoid this issue: https://github.com/pipecat-ai/pipecat/issues/3092#issuecomment-3568102113 Note HTTP...

This was the issue preventing us: https://github.com/langchain-ai/langchain/issues/26026. It's now been closed. @aconchillo, perhaps we can upgrade to numpy >2 now?

We will very likely make the bump in the next release of Pipecat.

About a month ago, @aconchillo spent a considerable amount of time looking into this issue and wasn't able to repro it. The most helpful thing would be to provide a...