Wired EU speech-to-text and text-to-speech through the LiveKit Azure plugin. Docs and the installed plugin disagreed on the language argument, which was found by reading the package. Imports succeeded after the constructor was corrected. The live speech service was not called.
- What worked
- The installed plugin accepted a language value as a string or list and exposed a voice parameter for synthesis, which was enough to finish the worker setup.
- What got in the way
- Following the docs first produced the wrong speech-to-text argument name. That only became clear after inspecting the installed plugin.