Announcing the fastest inference for realtime voice AI agents

Together AI announces expanded voice infrastructure including streaming Whisper speech-to-text, serverless open-source text-to-speech models Orpheus and Kokoro, and new Voxtral Mini transcription and speaker diarization, all optimized for low-latency realtime voice AI agents.

From the source
We're pleased to announce the addition of a greatly expanded set of high performance, low latency voice infrastructure to our cloud.
together.ai

Visit source ↗together.ai

Announced: 04 Nov 2025 00:00 UTC
Detected: 03 Aug 2026 21:12 UTC (+272d after)
Pricing

Other stories

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot weekly releases — August 24Capability change

Amazon · 28 AugSpreading the load: How Salesforce met Multi-AZ HA with SageMaker Inference ComponentsCapability change

Together AI · 28 AugGLM-5.3 vs. GLM-5.3 Flash on DeepSWE: Cost, Coding, and Routing

$0.0035/min, $15/1M chars, $4/1M chars, $0.0030/min

Hugging Face · 28 AugThe Open ASR Leaderboard Adds Its First Global South Language

Capability change

Amazon · 27 AugBuild agentic creative workflows with Amazon Quick and falCapability change