Compare

Kekoso vs TransPocket

Kekoso offers on-device dictation for macOS, whereas TransPocket is cloud-based and supports video.

Side by side

What it is
Kekoso:Kekoso provides on-device dictation, audio/video transcription and call recording for macOS, running locally on the Neural Engine.
TransPocket:TransPocket provides AI-enhanced audio and video transcription with fast processing and speaker recognition.
Best for
Kekoso:Local, no-cloud dictation and transcription
TransPocket:Fast, AI-powered audio/video transcription
Who it’s for
Kekoso:Mac users who need private, offline speech-to-text for apps, files, calls and AI agents.
TransPocket:Developers and content creators needing quick, accurate speech-to-text conversion.
Pricing
Kekoso:Paid
TransPocket:Freemium
Plans
Kekoso:—
TransPocket:Free $0 · Pro $10 per month
Works with
Kekoso:Claude Code, Claude Desktop
TransPocket:Whisper Large-v3 model
DevHunt upvotes
Kekoso:11
TransPocket:0
Launched on DevHunt
Kekoso:Sep 2026
TransPocket:Feb 2026

Kekoso features

  • Hotkey dictation. Press a shortcut to dictate into any active app; text appears where the cursor is.
  • File & YouTube transcription. Drop audio/video files or paste YouTube links to get local transcripts with timestamps.
  • Call recording with speaker separation. Record calls locally, split your microphone and the other side, and export labeled transcripts.
  • Local MCP transcription server. Runs a socket server so Claude, Codex and other agents can transcribe without API keys.
  • Custom vocabulary. Add or import word lists to enforce your terminology across all transcriptions.
  • Multiple model families. Choose between Parakeet, Whisper and SenseVoice models for speed, language coverage or CJK support.

TransPocket features

  • Ultra-Fast Processing. Transcribes audio/video instantly using Turbo model technology.
  • High Accuracy. Achieves an average Word Error Rate of 5.8% with Whisper Large-v3.
  • Multiple Formats. Supports MP3, MP4, WAV, M4A and other common audio/video files.
  • Speaker Recognition. Identifies and separates speakers, adding 20-30 s processing per file.
  • Live Recording. Records and transcribes audio in real-time.
  • YouTube Transcription. Transcribes YouTube videos by URL without downloading.
  • Export Options. Exports transcripts to DOCX, TXT, CSV, SRT, VTT and more.
  • Enterprise Security. Stores data in encrypted Amazon S3 with enterprise-grade protection.

Based on each tool's website and DevHunt data. Details may change; check the official sites.