Add Hume.ai TTS Support

[AbelRR]

What

This PR implements TTS support for Hume

Why

Adding initial support for Hume EVI-2

Docs

https://dev.hume.ai/reference/empathic-voice-interface-evi/chat/chat
https://dev.hume.ai/docs/empathic-voice-interface-evi/evi-2
https://dev.hume.ai/docs/empathic-voice-interface-evi/configuration

How to Test:

from agents/livekit-plugins run:
pip install -e ./livekit-plugins-hume --config-settings editable_mode=strict
from your pipeline agent, make sure to include a config_id from platform.hume.ai, that includes EVI-2, otherwise, EVI-1 will be used by default ⚠️:
hume.TTS(config_id="9b869872-xxx-xx-xxx")

[changeset-bot]

⚠️ No Changeset found

Latest commit: 56ef9c8

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

✅ AbelRR
❌ Your Name

---

Your Name seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[AbelRR]

Important to note while testing: while TTS works, there's a blip sound in between generations. this is similar to the sound at the start of deepgram TTS session.. Currently, this approach, opens and closes a websocket connection at each _run. Even when keeping a persistent WS connection, I still hear the blip sounds.

[AbelRR]

Important to note while testing: while TTS works, there's a blip sound in between generations. this is similar to the sound at the start of deepgram TTS session.. Currently, this approach, opens and closes a websocket connection at each _run. Even when keeping a persistent WS connection, I still hear the blip sounds.

This was resolved with extracting PCM data from WAV file.