What to expect from Flow: accuracy and known limitations

Flow turns speech into text and can clean up the result. Accuracy depends on the captured audio, language, and formatting settings. Use this guide to tell expected behavior apart from a problem worth troubleshooting.

An internet connection is required

Dictation is transcribed in the cloud. A brief connection failure can delay the result; if processing fails, reconnect and retry saved audio when offered. A microphone failure is different: uncaptured audio cannot be recovered. If network or VPN restrictions interfere, see network configuration.

Language and formatting can change the output

Flow supports more than 100 dictation languages, with varying accuracy and formatting quality. It records one detected language per dictation, not per word, so mixed-language speech can be less reliable — particularly English mixed with Chinese or Japanese.

• The dominant language wins: if you switch languages mid-dictation, the language you spoke longest is recorded for that dictation.

• Variants are recorded and exclusive: History shows the variant you selected — Hinglish, British or Canadian English, Traditional Chinese, Swiss German — rather than the base language, and variants in the same group are mutually exclusive. Choose the one you intend, since these affect spelling and script.

• Undetermined is a last resort: History records any language that was recognized; a dictation is marked undetermined only when no language could be identified at all.

• Formatting differs from mishearing: changed wording or layout in the pasted text is not the same as misheard speech. When words are missing, retry where available and compare the recorded audio.

See language settings for each platform's choices and the dictionary for recurring terms.

Long recordings can stop or take longer to process

A long dictation can finish in several parts, with processing time for each part, so the end of a long recording is not cut short. A connection interruption near the end can add processing time or leave an incomplete result: keep the session open while recovery runs, then use Retry in History if needed.

Back-to-back dictations

On desktop you can start a new dictation right after finishing one. If the earlier dictation is still being processed, the new recording waits its turn, then pastes and appears in History as usual. A dictation you dismiss with Escape while it is waiting is discarded without a result.

Text insertion depends on the app

Mac and Windows

Flow pastes text using the clipboard, so save important clipboard content before testing a troublesome app.

If insertion fails, follow the notification: it may offer manual paste or a Paste Last Transcript shortcut — Cmd+Ctrl+V on Mac and Shift+Alt+Z on Windows by default, or your configured shortcut. See text not pasting.

Android

Flow inserts into supported focused fields and can fall back to clipboard paste, which large or complex app screens may require. If transcription succeeded but insertion failed, use Paste; if transcription failed, use Retry once online.

Recovery depends on stored audio

On desktop, recovery uses the audio saved with the history entry, and Retry cannot run during an active dictation. See history and deletion for retention details.

Check audio before blaming the transcript

Wait briefly for the microphone before speaking, because wireless mics can need time to wake. Confirm the microphone you intend to use is selected as the input device. For an abrupt change in quality, follow Transcription suddenly got worse.

Still stuck?

Contact support if clear recorded speech consistently differs from the transcript. Include your platform and a specific example.