# VoiceAgentBench: Voice Benchmark Profile

> A multilingual voice-agent suite covering tools, workflows, multi-turn interaction, and safety.

- Scope: 5,500+ synthetic queries; 7 languages
- Measurement lanes: Task completion, Conversation dynamics
- Primary metric: Capability-specific task scores
- Available evidence: Paper and public dataset
- Owner: Krutrim AI Labs
- Source snapshots refreshed: 2026-09-18

## Interpretation limit

Its broad multilingual coverage is primarily synthetic, so it should not stand in for human-audio robustness.

## Primary sources

- [Paper](https://arxiv.org/abs/2510.07978)
- [Dataset](https://huggingface.co/datasets/krutrim-ai-labs/VoiceAgentBench)

Canonical page: https://benchlm.ai/voice-benchmarks/voiceagentbench