# NVIDIA 全双工语音模型工具调用新架构

- 来源：elvis (@omarsar0)
- 发布时间：2026-09-20 17:00
- AIHOT 分数：47
- AIHOT 链接：https://aihot.news/items/cmu9llf1x03smro9b3a15u83p
- 原文链接：https://x.com/omarsar0/status/2101597276242325864

## AI 摘要

NVIDIA 提出一种前后端架构，让全双工语音模型通过发出委托 token，将流式转录转发给文本后端 LLM 执行工具调用，再经轻量 prefill-and-repeat 机制回传结果并由 TTS 播报。

## 正文

NVIDIA research papers are on fire recently!

Here is another interesting paper where they give full-duplex speech models tool calls.

(bookmark it)

Commercial duplex voice models complete 31 to 51 percent of grounded customer-service tasks under clean conditions.

Text agents like GPT-5 reach 85 percent on the same tasks in text mode.

Most of what a voice agent loses, it loses in the speech pipeline.

The fix routes the decision out of the speech model.

The duplex frontend learns to emit a delegation token, forwards streaming transcripts to a text backend LLM for the tool call, and receives the result through a lightweight prefill-and-repeat mechanism before streaming TTS speaks it.

Tool-call recall runs 92.0 to 97.2 percent with 81.2 percent accuracy at rejecting irrelevant calls. Turn-taking rate, streaming ASR word error rate and spoken-language intelligence all stay at the no-tool-call baseline.

Paper: https://arxiv.org/abs/2609.19334

Chat with Paper: https://academy.dair.ai/papers/a-frontend-backend-architecture-for-tool-calls-in-full-duplex-speech-models-2609.19334