# Together AI — Announcing the fastest inference for realtime voice AI agents

- Company: Together AI (together.ai)
- Announced: 2025-11-04T00:00:00+00:00
- Category: capability-change
- Subject: Inference platform
- Models affected: Whisper, Orpheus, Kokoro, Voxtral Mini
- Pricing: $0.0035/min, $15/1M chars, $4/1M chars, $0.0030/min
- Source: https://www.together.ai/blog/the-fastest-inference-for-realtime-voice-ai-agents
- Record: https://forck.live/items/2401-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.

## Evidence

Verbatim from https://www.together.ai/blog/the-fastest-inference-for-realtime-voice-ai-agents:

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

---

Record: https://forck.live/items/2401-announcing-the-fastest-inference-for-realtime-voice-ai-agents
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md