# Best Current voice to voice API
**URL:**
**Author:**  [@kyars](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fkyars)%5C
**Post date:** [June 13, 2025, 3:56am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbest-current-voice-to-voice-api%2F159105%2F1 "2025-06-13T03:56:16Z")
Wondering what the best possible models currently available are for voice LLMs, as I have not found a benchmark for this.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [June 13, 2025, 5:15am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbest-current-voice-to-voice-api%2F159105%2F2 "2025-06-13T05:15:15Z")
There aren’t many speech-to-speech models to begin with, and ASR and TTS are difficult to benchmark… Because they are difficult to quantify.
Well, there are a few.
> **[Qwen/Qwen2.5-Omni-7B · Hugging Face](https://huggingface.co/Qwen/Qwen2.5-Omni-7B)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.
> **[Models - Hugging Face](https://huggingface.co/models?sort=trending&search=omni)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.
---
**Author:**  [@kyars](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fkyars)%5C
**Post date:** [June 13, 2025, 3:26pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fbest-current-voice-to-voice-api%2F159105%2F3 "2025-06-13T15:26:08Z")
thanks john!