[Cartesia] Upgrading the message cutoff for Cartesia Synthesizer to use timestamps

[chongzluong]

Overview

Discussed with Ajay over Slack, recapping below.

There's a distinction between Cartesia's version of continuations and Vocode's general expectation for continuations. Vocode seems to expect an N:N ratio of senders to receivers, but our continuations is an N:1 ratio of senders to receivers. Vocode's get_message_up_to also reflects this expected N:N approach.

The proposed solution to this is to start storing 2 new variables self.ctx_message and self.ctx_timestamps. The Cartesia TTS now requests timestamps, and those timestamps are used to indicate what message we've gotten up to. In the event that the timestamps aren't available for some reason, or in the event that timestamps are delayed beyond a 2 second gap, we fall back to using an estimated wpm and the self.ctx_message to get a best approximation.

Testing

I set up the telephony_app per the Vocode directions. I then adjusted the synthesizer and played around with it locally on my own Vocode deployment to check that it works as intended.

[ajar98]

will approve / merge once linting is good! can run make lint from the root dir

[cyrilS-dev]

This PR is causing an error :

vocode.streaming.synthesizer.cartesia_synthesizer:chunk_generator:185 - Caught error while receiving audio chunks from CartesiaSynthesizer: Failed to generate audio:
Error generating audio:
error processing TTS request: Language must be specified for timestamps.