Transcription Taking Too Long

Where Time Is Spent

A recording can spend time in several stages:

1. Loading or warming the transcription model.
2. Transcribing the audio.
3. Cleaning and formatting the text.
4. Running AI enhancement.
5. Pasting the result or generating an Assistant response.

Use Dashboard → View Insights → Model Performance to compare models for Today, Last 7 Days, Last 30 Days, This Year, or All Time. Use History -> Analyze for recording-level timing.

Local Models

Local transcription is usually fastest on Apple Silicon Macs. If you use an Intel Mac, cloud transcription providers are often much faster.

To improve local speed:

• Use Parakeet V3 or Parakeet V2 for fast local dictation.
• Try a smaller Whisper model if a large model is slow.
• Try Prewarm model (Experimental) in AI Models → gear → Transcription to prepare the model at launch or wake.
• Keep Voice Activity Detection enabled for local models to help separate speech from silence.

Large local models may take longer the first time they are prepared or loaded.

Cloud Transcription

Cloud transcription speed depends on provider latency, audio length, and your network connection. Groq, Deepgram, Mistral, Gemini, ElevenLabs, Soniox, Speechmatics, AssemblyAI, xAI, Cartesia, and OpenRouter are available as cloud transcription options depending on the provider capability.

See Cloud Providers.

AI Enhancement

AI enhancement adds a second model call after transcription. If the raw transcription is fast but the final output is slow, check the Mode's AI enhancement provider and model.

To reduce enhancement delay:

• Disable AI enhancement for simple Dictation Modes.
• Enable Skip short transcriptions in AI Models -> gear -> Enhancement.
• Increase or decrease Timeout Duration based on your tolerance.
• Choose On timeout → Retry when you want another attempt after a timeout; up to three attempts can increase the total wait.
• Try a faster enhancement provider or model.

See Model Settings and Mode Settings.

File Transcription

Long audio and video files naturally take longer than live dictation. The Transcribe view shows queue states such as Loading model, Processing audio, Transcribing, Enhancing, Completed, and Failed, so you can see where the delay is happening.

See Transcribe Audio Files.

Timeout Settings

The shared transcription Timeout applies to batch cloud requests, not local processing or streaming. Enhancement has a separate timeout and retry policy. Local CLI defaults to its own 45-second command timeout. See Model Settings and Local CLI.