
Deepgram STT is now natively available on @togethercompute. One platform, full voice-agent stack: Deepgram transcription, Together-hosted LLMs, Aura-2 TTS. Sub-3-second round trip on reference builds. If you're prototyping a voice agent and bouncing between four vendors, you can stop. Build your voice agent on the Together x Deepgram stack: https://t.co/hQC99KrhKi.

Deepgram transcription is now callable natively on Together AI next to hosted LLMs and Aura-2 TTS, so a voice prototype runs through one platform instead of stitching three or four vendors together.
Checking sign-in…
Loading comments…