T9-R1 quiz
What order does LiveKit give for a cascaded pipeline? Answer: Speech-to-text, then a language model, then text-to-speech. That is the order on the pipeline page.
What does a realtime model skip, on that page? Answer: A separate transcription step on the way in and a separate TTS on the way out. The page says speech goes in and speech comes out of one model.
Are speech-to-speech, text-to-speech, and speech-to-text the same API on that Voice overview? Answer: No. The overview presents them separately.. The overview gives each its own section.
Sources and go deeper
- LiveKit Agents, Pipeline types vendor last checked 2026-10
- Pipecat open source framework vendor last checked 2026-10
- Voice Overview, docs.x.ai vendor The page calls them SpaceXSI Voice APIs, powered by Grok, and separates Speech to Speech, Text to Speech, and Speech to Text. last checked 2026-10