Speech-to-text latency, measured

Every transcription we run times the provider that answered it. These are those timings — 0 provider attempts over the last 30 days, grouped by the region that made the call.

Metric

Clip length

No measurements for this clip length yet.

Nothing has been recorded for “Under 10 seconds” in the last 30 days. Pick another clip length above — this page fills in as transcriptions run.

How this is measured

What the number is: The time one provider took to answer one call, measured at the edge machine that made it — everything that attempt spent, including handing the audio to the provider and waiting on a long-running job. Your upload to us, authentication, and our own credit checks are excluded. So is the network between you and us — this is the provider's time, not your round trip.
Failed attempts count: A provider that times out still spent your time, so its attempt is in the latency numbers. When one provider fails we fall back to another, and both attempts are recorded separately. The error-rate metric shows how often that happens. What is never counted is a request we turn away ourselves before calling anyone — audio past a provider's size cap, or in a format it does not accept: that provider never received the call, so it is not charged for it here.
A row is a provider, not a model: Most of these providers offer several models, and HyperWhisper lets you pin the one you want. A row covers whichever model of that provider actually ran — its default for most people, plus whatever anyone else picked — so read a row as “how fast this provider answers us”, not as a benchmark of one named model against another.
Why clip length matters: Longer audio takes longer to transcribe, so comparing a provider handed 5-second clips against one handed 5-minute files would say nothing. Every cell compares clips of similar length, grouped by an estimate taken from the audio's size and format — the same estimate for every provider, so no cell is flattered by a provider that measures its own audio differently.
What it covers: The batch transcription endpoint. Live streaming transcription is not measured here.
What we store: A timing row carries the provider, the model, the region, which clip-length group the audio fell in, which attempt in the chain it was, and whether the call worked. It carries no account, no key, no request id, and no audio or text. The clip's own length is not kept, and the timestamp is stored only to the hour, so nothing ties a row to a person or reassembles one transcription.
How to opt out: In the HyperWhisper app, turn off Share anonymous speed data under Settings → General. Your transcriptions work exactly the same — the same providers, the same speed, the same result — we just stop keeping the timing. Calling the API yourself? Send X-Latency-Opt-Out: 1. Local models never send a timing at all.

How this is measured

What the number is

The time one provider took to answer one call, measured at the edge machine that made it — everything that attempt spent, including handing the audio to the provider and waiting on a long-running job. Your upload to us, authentication, and our own credit checks are excluded. So is the network between you and us — this is the provider's time, not your round trip.

Failed attempts count

A provider that times out still spent your time, so its attempt is in the latency numbers. When one provider fails we fall back to another, and both attempts are recorded separately. The error-rate metric shows how often that happens. What is never counted is a request we turn away ourselves before calling anyone — audio past a provider's size cap, or in a format it does not accept: that provider never received the call, so it is not charged for it here.

A row is a provider, not a model

Most of these providers offer several models, and HyperWhisper lets you pin the one you want. A row covers whichever model of that provider actually ran — its default for most people, plus whatever anyone else picked — so read a row as “how fast this provider answers us”, not as a benchmark of one named model against another.

Why clip length matters

Longer audio takes longer to transcribe, so comparing a provider handed 5-second clips against one handed 5-minute files would say nothing. Every cell compares clips of similar length, grouped by an estimate taken from the audio's size and format — the same estimate for every provider, so no cell is flattered by a provider that measures its own audio differently.

What it covers

The batch transcription endpoint. Live streaming transcription is not measured here.

What we store

A timing row carries the provider, the model, the region, which clip-length group the audio fell in, which attempt in the chain it was, and whether the call worked. It carries no account, no key, no request id, and no audio or text. The clip's own length is not kept, and the timestamp is stored only to the hour, so nothing ties a row to a person or reassembles one transcription.

How to opt out

In the HyperWhisper app, turn off Share anonymous speed data under Settings → General. Your transcriptions work exactly the same — the same providers, the same speed, the same result — we just stop keeping the timing. Calling the API yourself? Send X-Latency-Opt-Out: 1. Local models never send a timing at all.