What the no-upload trade-off actually costs
A speech model that fits in a browser is smaller than one running on a server rack. Here is the size of that gap, measured on the same audio, for all nine languages.
word error rate, lower is better · FLEURS test · n = 111–120 · 2026-09-26
How this was measured
Both systems were given the same 150 sentences per language from Google’s FLEURS test set, on the same machine, and scored with the same normalisation: case and punctuation ignored. A sentence is excluded entirely if its reference text, or either system’s output, contains digits — “1940” and “nineteen forty” are both correct, and no single rule normalises that across nine languages. The same sentences are dropped for both systems, and dropping them widens the gap rather than narrowing it. The reference system is Whisper large-v3, the model most free online transcription services run, quantised to q5_0. Many free services actually run a smaller Whisper variant, so the gap shown here is the widest you should expect.
What these numbers do not tell you
FLEURS is read speech recorded in quiet conditions, so both columns are optimistic compared with a real meeting recording. Read the gap between the columns, not the absolute values. FLEURS also ships only Latin-American Spanish and Brazilian Portuguese, so the European variants of those two are not measured separately.
Speed is the share of real time needed to transcribe: 0.20× means a one-hour recording takes twelve minutes. Measured on an Apple M-series laptop; your machine will differ.