Tag

#voice-agents

Posts tagged with voice-agents

5 posts

The Deepgram Daily acquisition places the speech model, transport, and orchestration layers of the Pipecat voice stack under one owner while the framework stays open source.

News • Oct 29, 2026 •11 min read

What the Deepgram Daily Acquisition Actually Protects

The Deepgram Daily acquisition keeps Pipecat forkable. What it cannot protect is governance, merge rights, and integration parity. Five signals to watch.

#pipecat #deepgram +4

Steerable text to speech lets an LLM voice agent adjust pitch, rate, and loudness numerically mid-conversation.

Tools • Oct 19, 2026 •12 min read

SteerTTS Review, a Prosody Control Plane for Voice Agents

SteerTTS review: does z-score prosody control work as the control plane for LLM voice agents? Latency math, CPU feasibility, and a steerability harness.

#steertts #text-to-speech +4

Nemotron 3 Diarization turns speaker labeling from a metered API line item into a compact model small enough to fold into existing voice agent infrastructure.

News • Sep 27, 2026 •10 min read

Nemotron 3 Diarization Flips the Speaker Labeling Math

Nemotron 3 Diarization is a free 100M-parameter model. We break down pipeline placement for voice agents, run-cost math, and when to self-host diarization.

#nvidia #nemotron +4

Gemini 3.8 Live extended thinking lets a realtime voice agent reason before speaking, and that reasoning pause must fit inside a strict end-to-end latency budget.

Tools • Sep 17, 2026 •10 min read

Gemini 3.8 Live Extended Thinking Needs a Latency Budget

Gemini 3.8 Live extended thinking adds reasoning time to a realtime voice agent. The latency-budget math tells you when it helps and when it is dead air.

#gemini-38 #extended-thinking +3

TontaubeV1 review with reproducible VRAM and latency math for running a 2.9B open-weight text-to-speech model locally.

Tools • Sep 01, 2026 •12 min read

TontaubeV1 Review With Serving Math You Can Run

This TontaubeV1 review audits the 2.9B character-level TTS model with serving math builders can verify, covering VRAM, latency, and long-form narration.

#tts #local-inference +4