· Updated
Sonic-3, Sonic-2) and Deepgram (speech recognition and synthesis), alongside Whisper, Minimax Speech, Rime, and Kokoro. Teams get one API, one billing surface, and can swap models across the full stack without rebuilding integrations. Enterprise tiers include SOC 2 Type II, HIPAA, and dedicated data residency.Multi-vendor voice stacks route audio and text across the public internet at every handoff — adding latency and complexity. Running the full pipeline on local datacenter networking, Together delivers end-to-end latency under 700ms for natural turn-taking. The modular design preserves intermediate transcripts, giving teams data-routing control that opaque speech-to-speech systems don't offer.
Configure your preferred STT, LLM, and TTS models from Together's catalog and swap them independently as your requirements evolve.
Today, Together AI is launching a unified solution for building real-time voice agents with the entire pipeline running on one cloud. AI natives can now deploy voice apps for every use case at production scale. https://t.co/GhdUWdhEU4
More like this
OpenRouterMay 7
CloudflareApr 16
OpenAIApr 28
ElevenLabsMay 7