deepgramCommand-line tool for fast, accurate speech-to-text transcription from local files, URLs, or live audio using Deepgram’s API with customizable options.
Install via ClawdBot CLI:
clawdbot install nerkn/deepgramGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://example.com/audio.mp3Audited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
Journalists can use the Deepgram CLI to transcribe recorded interviews from local audio files or remote URLs, enabling quick conversion of spoken content into text for article writing. By applying options like diarization, they can separate speakers and add punctuation for clarity, streamlining the editing process and improving accuracy.
Businesses can transcribe customer support calls stored as audio files to analyze interactions for quality assurance and training purposes. Using flags like language detection and speaker diarization helps identify key issues and speaker roles, facilitating insights into customer sentiment and agent performance.
Educators and institutions can transcribe lectures from microphone input or prerecorded files to create subtitles in formats like SRT or VTT for accessibility. This supports students with hearing impairments and enhances learning materials by providing searchable text versions of audio content.
Podcast producers can use the CLI to transcribe episodes from local files or URLs, generating transcripts for show notes, SEO optimization, and audience engagement. With options for plain text output, they can easily edit and repurpose content across platforms like blogs or social media.
Offer transcription services using the Deepgram CLI to process audio files for clients like researchers or businesses, charging per minute or project. Leverage the CLI's speed and accuracy to handle multiple formats and languages, scaling operations with scriptable workflows for bulk jobs.
Integrate the Deepgram CLI into a software-as-a-service platform that provides automated transcription APIs for applications in media or customer support. Monetize through API usage tiers, offering features like real-time transcription and advanced options to attract enterprise clients.
Sell a toolkit that includes the Deepgram CLI for content creators, such as YouTubers or educators, to generate transcripts and subtitles for videos. Bundle with training and support, focusing on ease of use and output formats to enhance video accessibility and SEO.
💬 Integration Tip
Use the CLI's pipe-friendly design to integrate with existing scripts or workflows, such as automating transcript generation from uploaded audio files in a web application.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
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.
Local text-to-speech via sherpa-onnx (offline, no cloud)
Start voice calls via the OpenClaw voice-call plugin.