Skip to content
SPECIFICTION
Get listed

Kekoso vs Whisper

Kekoso

kekoso.app

Whisper

github.com

Side by side

FigureKekosoWhisper
Price from—$0.01/mo
Free plan—Yes
Free trialYes—
Open source—Yes
Windows—Yes
macOSYesYes
Linux—Yes
API—Yes
Self-hosted—Yes
Plans published23
Spec score · AI Video Caption Generators7.7 (#78)9.5 (#1)
PurposeKekoso provides Mac voice dictation, audio and video transcription, call recording, and a local MCP transcription server for AI agents.Whisper is a general-purpose speech recognition model for multilingual transcription, speech translation, and language identification.
TranslationTranslation is off until configured, requires the user’s OpenRouter key, and sends recognized text rather than audio.Whisper can translate speech from multiple languages into English.

Plans

Kekoso

  • Kekoso licence$29, paid once
  • Kekoso$29, paid once

Kekoso pricing →

Whisper

  • Self-hosted WhisperFree
  • Whisper (open-source code and model weights)Free
  • Whisper API$0.01 a month

Whisper pricing →

In their own words

Kekoso

Kekoso has no write-up on Specifiction yet; its figures are above.

Visit kekoso.app

Whisper

Whisper is an open-source speech recognition model for transcription, speech translation, language identification, and voice activity detection. Its documented command-line and Python interfaces process audio files, and it can translate speech from multiple languages into English. The repository lists six model sizes—tiny, base, small, medium, large, and turbo—with different speed and memory tradeoffs; stated VRAM needs range from about 1 GB to 10 GB, depending on size. Installation is documented through pip and requires the ffmpeg command-line tool. Rust may be needed if a prebuilt tiktoken wheel is unavailable. The code and model weights are released under the MIT License, with local installation using Python and ffmpeg. Whisper is listed for Linux, macOS, Windows, and self-hosted deployment. OpenAI says it was trained on 680,000 hours of multilingual and multitask supervised data collected from the web. Performance varies widely by language, and it does not outperform models specialized for LibriSpeech. Turbo is not trained for translation; multilingual models are recommended for translating non-English speech into English.

Visit github.com