Models / Aqua Voice/ Avalon v1 en

Avalon v1 en

Aqua Voice

Speech to textTranscribes a recording into words

Input: audio. Output: text.InputOutput
Type
Proprietary
Input
None held
Output
None held
Cached
None held

We don't hold a list price for this model yet · hosted only — no weights published

Our take

Written Aug 2, 2026

Avalon v1 is Aqua Voice's proprietary English-only speech-to-text model that excels at clean, prepared audio but falls apart on challenging real-world recordings. It is a specialist tool for high-stakes transcription of polished English speech, not a general-purpose dictation engine.

Who should pick it

Pick this for high-stakes transcription of clean, prepared English speech where every word matters — it misses roughly one word in 79 on read-aloud audio. Use it for financial earnings calls or European-accented English, where it performs almost as well. Skip it if you are transcribing meetings, podcasts, video, or any accented English outside European varieties, where its error rate jumps more than sixfold.

The case for it

  • Near-perfect on clean read-aloud English: roughly one word wrong per 79 words.
  • Strong on financial domain audio, with an error rate close to its clean-speech performance.
  • European-accented English handled notably better than accented speech generally.

The case against it

  • Dramatically worse on real-world, unscripted audio: error rate jumps more than sixfold on podcasts and video, and nearly eightfold on recorded meetings.
  • Struggles with non-European accented English, where the error rate is almost six times higher than for European accents.
  • No commercial access currently available and no verified multilingual capability.
00

How good is it?

TranscriptionTurning speech into text3.5 of 5Open ASR WER · 24th of 74

Words it gets right

94.8%

Misses roughly one word in 19, averaged over nine English test sets.

Where it struggles
Read aloudaudiobooks, clean recording1.3%
Podcasts and videoeveryday internet audio8%
Accented speechspeakers from many countries11%
Meetingsa room, several people, far microphone9.7%

Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case, not to the board.

The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.

Also scored, on boards we give no mark for
European-accented speech 3rd of 74Financial calls 14th of 74Clean read speech 28th of 74Harder read speech 28th of 74Podcasts and video 30th of 74Recorded meetings 32nd of 74Accented speech 40th of 74

These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.

Every published score for this model8 scoresEvery figure we hold, from 8 boards, with who ran it and a link to the source — including the boards no rating above is built on.
5.2independentsource ↗
11independentsource ↗
1.9independentsource ↗
9.7independentsource ↗
1.3independentsource ↗
2.9independentsource ↗
01

Where to get it

We hold no priced listing for Avalon v1 en.

There is no copy to download and no host in our price data, so Aqua Voice is where to look. We watch OpenRouter, the provider APIs we track and the LiteLLM price set; this version appears in none of them, which is a gap in what we collect rather than a statement about what Aqua Voice sells.

02

When we formed this view

Dates behind this page

Aug 2, 2026BenchmarkScored 11 on Accented speechleaderboard
Aug 2, 2026BenchmarkScored 1.9 on Financial callsleaderboard
Aug 2, 2026BenchmarkScored 9.7 on Recorded meetingsleaderboard
Aug 2, 2026BenchmarkScored 1.9 on European-accented speechleaderboard
Aug 2, 2026BenchmarkScored 8 on Podcasts and videoleaderboard
Aug 2, 2026BenchmarkScored 1.3 on Clean read speechleaderboard
Aug 2, 2026BenchmarkScored 2.9 on Harder read speechleaderboard
Aug 1, 2026ListedListed on LLMapfirst indexed by our pipeline
Aug 1, 2026BenchmarkScored 5.2 on Open ASR WERleaderboard

Prices last checked 6h ago

What we do not know about this model yet

  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
  • We don't hold a list price for this model yet — the gap is ours, not the lab's.
03

Licence and identifiers

What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.

Licence

Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.

Identifiers

Modality record
audio->text
Catalogue slug
aquavoice-avalon-v1-en

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us