← Speech-to-Text

Gladia

Solaria-1

Gladia’s higher-accuracy Solaria-3 has no live endpoint — pre-recorded only.

Measured 2026-10-01

Run Solaria-1 on Speko →

One API, every model on this board.

WER · batch

5.0%

WER · streaming

Read speech

11.21%

Conversation

21.15%

Details

Read speech

n=1541 · FLEURS test+dev+train · vendor-direct

2 of 1541 clips came back empty, scored as all-deletion.

Conversation

18.0–24.4% · EdAcc n=283 · 60 speakers, 2 passes, 2026-10-01

Finalize

910ms

p50–p90 · US East · n=199 · vendor-direct · ±6%

Vendor-default endpointing (0.05s of silence). Gladia often splits one sentence into several finals; this times the last.

Time to first token

1.61s

p50–p90 · US East · n=199 · vendor-direct · ±8%

The probe turns on partials, which Gladia disables by default. Without them this would time the first final.

Cost / min

$0.0125

Starter pay-as-you-go real-time ($0.75/hr). Pre-recorded is $0.0102/min, and committed Growth pricing goes to $0.0042.

Share this result

Embed the live badge

Speko stt rank
Markdown
[![Speko stt rank](https://speko.ai/benchmarks/badge/stt/gladia-solaria-1.svg)](https://speko.ai/benchmarks/stt/gladia-solaria-1)
HTML
<a href="https://speko.ai/benchmarks/stt/gladia-solaria-1"><img src="https://speko.ai/benchmarks/badge/stt/gladia-solaria-1.svg" alt="Speko stt rank"></a>
URL
https://speko.ai/benchmarks/stt/gladia-solaria-1