Passa al contenuto principale

Come Funziona la Dettatura

TalkWriter transforms your voice into polished, ready-to-use text through a multi-stage pipeline. This page explains each step so you understand exactly what happens between pressing the Fn key and seeing text appear.


The Dictation Pipeline​

When you dictate, your voice passes through four stages:

🎤 Voice Input → 📝 Speech-to-Text → ✨ AI Polish → 📋 Paste

Each stage builds on the previous one. Here is what happens at each step:


Stage 1: Voice Input​

What happens: Your microphone captures your voice and TalkWriter streams the audio data to the cloud in real time.

  • Your Mac's built-in microphone, an external USB mic, or Bluetooth headset captures audio.
  • TalkWriter streams audio as you speak. It does not wait until you finish.
  • The pill overlay shows an animated waveform to confirm audio is being detected.
suggerimento

For the best results, speak clearly and keep your microphone 6-12 inches from your mouth. See Microphone Best Practices for detailed setup tips.


Stage 2: Speech-to-Text (Soniox STT)​

What happens: A professional-grade speech recognition engine (Soniox) converts your audio into raw text.

  • Soniox processes your audio stream in real time with low latency.
  • It supports 100+ languages and can handle accents, fast speech, and technical vocabulary.
  • The raw output is unformatted: no punctuation, no capitalization corrections, and filler words are included.

Example raw output:

hey um i wanted to follow up on our meeting from yesterday i think the project timeline looks good but uh we might need to push the design review back a week


Stage 3: AI Polish​

What happens: TalkWriter's AI engine cleans up the raw transcription and produces natural, well-formatted text.

AI Polish performs these transformations:

TransformationBeforeAfter
Remove filler words"um", "uh", "like", "you know"Removed
Add punctuation"hello how are you""Hello, how are you?"
Fix capitalization"i went to new york""I went to New York"
Format numbers"twenty five dollars""$25"
Clean sentence structure"so basically the thing is that"Direct phrasing

Example polished output:

Hey, I wanted to follow up on our meeting from yesterday. I think the project timeline looks good, but we might need to push the design review back a week.

Funzione Pro

TalkTone adds an extra layer after AI Polish. If you have Pro, your text is rewritten to match a selected writing style (Professional, Casual, Academic, etc.). Upgrade now →


Stage 4: Paste​

What happens: The polished text is inserted at your cursor position in whatever app is active.

  • TalkWriter simulates a keyboard paste action using macOS Accessibility.
  • Text appears wherever your cursor was when you started dictating.
  • The pill overlay briefly shows a checkmark to confirm the paste.

Pipeline Summary​

StageEngineHappensSpeed
Voice InputYour microphoneLocally on your MacInstant
Speech-to-TextSoniox (cloud)Real-time streaming~200ms latency
AI PolishTalkWriter AI (cloud)After speech ends~500ms-1s
PastemacOS AccessibilityLocally on your MacInstant
note

Total time from releasing the Fn key to seeing text: typically under 2 seconds for short dictations. Longer passages may take slightly more time for AI processing.


Frequently Asked Questions​

Can I skip AI Polish and get raw transcription? Yes. Toggle AI Polish off in Settings > AI Polish. You will get the unformatted Soniox output directly.

Is my audio stored on the server? Audio is streamed for real-time processing and is not permanently stored. See our privacy policy for details.

Why does TalkWriter need the internet? Both the speech-to-text engine (Soniox) and AI Polish run in the cloud. An internet connection is required for all dictation.

What happens if my internet drops mid-dictation? TalkWriter will show an error on the pill overlay. Any audio captured before the disconnection may still be processed, but results are not guaranteed.


Ti è stato utile? Faccelo sapere su support@talkwriter.ai