parakeet-mlxLocal speech-to-text with Parakeet MLX (ASR) for Apple Silicon (no API key).
Install via ClawdBot CLI:
clawdbot install kylehowells/parakeet-mlxInstall Parakeet MLX CLI (uv tool install):
Install Parakeet MLX CLI (uv tool install)Requires:
Use parakeet-mlx to transcribe audio locally on Apple Silicon.
Quick start
parakeet-mlx /path/audio.mp3 --output-format txtparakeet-mlx /path/audio.m4a --output-format vtt --highlight-wordsparakeet-mlx *.mp3 --output-format allNotes
uv tool install parakeet-mlx -U (not uv add or pip install)parakeet-mlx --help to see all options (--help, not -h).~/.cache/huggingface on first run.mlx-community/parakeet-tdt-0.6b-v3 (optimized for Apple Silicon).ffmpeg installed for audio processing.--verbose for detailed progress and confidence scores.*.mp3 work).Generated Mar 1, 2026
Podcasters can transcribe episodes locally on Apple Silicon Macs to create text versions for SEO, accessibility, and repurposing into blog posts. This avoids API costs and keeps sensitive content private.
Small teams can transcribe internal meetings or client calls from recorded audio files to generate minutes or action items. It runs offline, ensuring data security and reducing reliance on cloud services.
Educators and students can transcribe recorded lectures or tutorials to create study notes, subtitles for videos, or accessible materials for learners. Local processing handles multiple files efficiently.
Journalists can transcribe interviews from audio recordings for accurate quotes and article drafting. The local setup protects source confidentiality and works without internet access.
Healthcare professionals can transcribe patient notes or dictations locally to maintain HIPAA compliance and avoid cloud-based transcription services. It supports various audio formats for flexibility.
Offer a free tier for basic transcription with limited features, then charge for advanced options like batch processing, custom models, or priority support. Integrate with existing productivity tools.
Sell licenses to large organizations needing secure, offline transcription for sensitive data, such as legal or healthcare firms. Include installation support and custom training.
Package the CLI as part of a developer toolkit or API for embedding transcription into custom applications. Charge based on usage volume or offer a one-time purchase for self-hosted deployments.
💬 Integration Tip
Ensure ffmpeg is installed system-wide for audio processing, and use shell wildcards like *.mp3 to batch transcribe multiple files efficiently.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
End-to-end encrypted agent-to-agent private messaging via Moltbook dead drops. Use when agents need to communicate privately, exchange secrets, or coordinate without human visibility.
Text-to-speech via OpenAI Audio Speech API.