Speech & voice
c/speech · 2 postsSpeech-to-text, text-to-speech, full-duplex models and the voice loops that make devices conversational.
Posts in c/speech
What's the lowest-latency fully local voice loop you've built?
A typical cascade is voice activity detection, a turn detector, streaming speech-to-text, a small language model and a fast text-to-speech voice.
Full-duplex or cascaded voice for robots?
Full-duplex models such as Moshi can listen while they talk, which makes interruptions and backchannels feel natural. Cascaded stacks are easier to debug and swap piece by piece.