Skip to content
knecty

Voice input and read aloud

Dictate a message

  1. Tap the microphone next to the message box. The first time, your browser asks for permission to use the microphone — allow it.
  2. Speak. Tap the red square (Stop recording) when you’re done. Recording stops by itself after 2 minutes.
  3. Knecty turns your speech into text and adds it to the message box. It isn’t sent automatically — check it, edit it, and send when ready.

The language is detected automatically, so you can speak in any language the model understands.

What it costs

1¢ per MB of audio, rounded up, with a minimum of 1¢ per recording. A typical short message is 1¢. It’s charged when your recording is transcribed, from the same wallet as everything else; if transcription fails, it’s refunded.

Read aloud

Tap Read aloud on a reply to hear it, and Stop reading to stop. This uses your browser’s built-in voice, so it’s free and nothing is sent to us. Code blocks are read as “code block”. If your browser has no speech voice, the button doesn’t appear.

If voice doesn’t work

  • “Microphone access was blocked” — allow the microphone for this site in your browser’s settings, then try again.
  • “Voice input isn’t supported in this browser” — use a current version of Chrome, Edge, Firefox or Safari.
  • “Transcription timed out” — try again, or record a shorter clip.
  • “Daily voice transcription limit reached” — there’s a daily limit; try again tomorrow.
  • “Not enough usage balance for voice input” — top up, or wait for your weekly credit.