# Baseten — Baseten leads Coval’s voice AI benchmark

- Company: Baseten (baseten.co)
- Announced: 2026-09-08
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://www.baseten.co/blog/baseten-leads-covals-voice-ai-benchmark
- Record: https://forck.live/items/32772-baseten-leads-coval-s-voice-ai-benchmark
- Subject: Baseten
- Models affected: Qwen3 ASR 1.7B Streaming, Qwen3 TTS 12Hz Base Streaming 1.7B

Baseten says it sits at the top of Coval's early-access voice AI benchmarks, placing its speech-to-text deployment on the quality-latency Pareto frontier. Coval is a voice AI evaluation platform that runs reproducible, independent benchmarks, and its September 2026 early-access results measure what end users experience: speed and accuracy together for speech-to-text, and time to first audio for text-to-speech. Baseten says its STT deployment is about 5× faster than OpenAI's while also showing the best word error rate, which it argues shows optimized inference can improve responsiveness without sacrificing transcription quality. Baseten says it defines the frontier with Qwen3 ASR 1.7B Streaming for STT and Qwen3 TTS 12Hz Base Streaming 1.7B for TTS, and that no provider in the current benchmark is faster while also producing a lower error rate, as of Oct 1., 2026. It also leads the TTS quality benchmark and sits on the quality-latency frontier there. Baseten argues a voice agent's latency compounds across speech-to-text, reasoning, text-to-speech, orchestration and networking, so a strong median latency can hide a p95 that hurts some conversation turns. Coval's benchmark runs from a fixed region for fairness and reproducibility, and Baseten says its deployments enter it as normal API endpoints backed by dedicated inference hardware.

## Evidence

Verbatim from https://www.baseten.co/blog/baseten-leads-covals-voice-ai-benchmark:

> Baseten leads Coval’s voice AI benchmark by sitting on the quality-latency Pareto frontier: its STT deployment is about 5× faster than OpenAI’s while also delivering the lowest WER. Production voice AI performance is not just about model choice, it depends on the full inference stack, from STT and TTS latency to orchestration, networking, autoscaling, and deployment placement.
> 
> Coval is a voice AI evaluation platform that helps teams test, compare, and improve AI agents with reproducible, independent benchmarks. Its open benchmark methodology highlights the core inputs behind every leaderboard result: the dataset, provider model versions, normalization pipelines, and latency measurement approaches.
> 
> In Coval’s early-access benchmarks in September 2026, Baseten is positioned at the top of the leaderboard, sitting on the quality-latency Pareto frontier. The benchmark measures what end-users experience: for speech-to-text (STT), that means evaluating both speed and quality together. For text-to-speech (TTS), latency (or time to first audio) determines whether the agent feels responsive.

---

Record: https://forck.live/items/32772-baseten-leads-coval-s-voice-ai-benchmark
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
