AI tool comparison
Cohere Transcribe vs Ghost Pepper
Which one should you ship with? Here is the side-by-side panel verdict, pricing read, reviewer split, and community vote comparison.
Audio & Speech
Cohere Transcribe
#1 open-source ASR model — 5.42% WER, beats Whisper Large v3
75%
Panel ship
—
Community
Paid
Entry
Cohere Transcribe (cohere-transcribe-03-2026) is a 2B-parameter automatic speech recognition model released under Apache 2.0. It uses a Conformer-based encoder–decoder architecture with more than 90% of parameters in the encoder, keeping autoregressive decode compute minimal while delivering state-of-the-art accuracy. On the HuggingFace Open ASR Leaderboard, it achieves a 5.42% average word error rate — #1 overall, beating Whisper Large v3, ElevenLabs Scribe v2, and Qwen3-ASR-1.7B. It supports 14 languages including English, German, French, Arabic, Chinese, Japanese, and Korean, and runs up to 3x faster in real-time factor than comparable dedicated ASR models in its size range. The model is available for download on HuggingFace and through Cohere's commercial API. For enterprise deployments, it can be run fully on-premise under its permissive license — a significant differentiator from closed ASR services like Whisper or ElevenLabs Scribe.
Voice & Dictation
Ghost Pepper
Hold Control. Speak. Release. It types for you — all on-device.
75%
Panel ship
—
Community
Free
Entry
Ghost Pepper is a macOS hold-to-talk dictation app that runs entirely on-device using Apple's WhisperKit for speech recognition and LLM.swift for smart cleanup. You hold the Control key to record, release to transcribe, and the transcribed text is automatically pasted into whatever app you're using. No cloud, no subscription, no data ever leaves your Mac. The "smart cleanup" feature is what sets it apart from basic Whisper wrappers: it uses a local language model to remove filler words, fix self-corrections in real time, and clean up stutters without altering your intent. Version 2.0.1, released April 6, brings improved accuracy and lower latency on Apple Silicon. It requires macOS 14+ and an Apple Silicon chip. Ghost Pepper hit the top of Hacker News' Show HN section on April 7 with 354 points and 164 comments — an unusually strong signal for a solo-dev open-source tool. The timing is notable: as commercial dictation tools like Wispr Flow move to paid-only models, Ghost Pepper offers a fully free, auditable alternative. It's MIT-licensed and available on GitHub.
Reviewer scorecard
“A 2B-param model that beats everything on the ASR leaderboard, Apache 2.0 licensed, running 3x faster than comparable models — this is the new default for speech integration. I'm ripping out the Whisper pipeline this week and not looking back.”
“This is the dictation tool I've been waiting for. On-device, zero latency once warmed up, MIT license, and the LLM cleanup actually works. I replaced Wispr Flow with this in under 5 minutes. The Control-hold UX is more ergonomic than I expected.”
“SOTA leaderboard performance doesn't always translate to production resilience. Whisper has years of community testing, edge case handling, and tooling built around it. Cohere Transcribe is impressive on benchmarks, but run it against your actual data distribution — accents, noise, domain vocab — before committing to a migration.”
“Apple Silicon only and macOS 14+ means a significant portion of Mac users are locked out. The 'smart cleanup' LLM adds another model to memory — not ideal if you're already running other local models. Also, no GUI means non-technical users won't touch it.”
“The open-sourcing of a frontier ASR model by an enterprise AI company signals that speech recognition commoditization is complete. Cohere just made accurate transcription a commodity — the value moves entirely to what you build above the transcript layer. Voice interfaces just got dramatically cheaper to bootstrap.”
“Ghost Pepper is a preview of how computing will feel in 5 years: ambient voice input everywhere, zero latency, zero cloud dependency. The fact that a solo dev shipped this in Swift using WhisperKit and LLM.swift is a testament to how capable the Apple Neural Engine stack has become.”
“Finally a transcription model I can run locally at SOTA quality. For podcast editing, video captioning, and multilingual content workflows, this hits every requirement: accuracy, speed, multilingual support, and the ability to run completely offline without paying per-minute fees.”
“I tried it during a writing session and the filler-word removal alone is worth it — my raw dictation comes out cleaner than when I type. The hold-to-talk model also means I'm never accidentally recording. Solid privacy story for journaling and creative work.”
Weekly AI Tool Verdicts
Get the next comparison in your inbox
New AI tools ship daily. We compare them before you waste an afternoon.