synesthesiam/voice2json

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

1105 stars · 65 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

voice2json is a collection of command-line tools for offline speech-to-text and intent recognition on Linux, supporting 18 languages via engines like Pocketsphinx, Kaldi, DeepSpeech, and Julius. It outputs JSON events with recognized text, intent names, and slots, and integrates into Unix workflows and voice assistant setups.

Use cases

• add offline voice commands to existing applications or unix workflows
• transcribe wav audio to text from the command line
• recognize intents and slots from spoken commands as json
• build a fully offline voice assistant on modest hardware
• create an mqtt transcription service
• bootstrap a rasa nlu chatbot with speech input

When to choose

• you need completely offline speech and intent recognition on linux
• your voice commands fit a grammar with uncommon words or custom pronunciations
• you want to pipe speech recognition into unix-style workflows or scripts
• you need to run on modest hardware without cloud services

When to avoid

• you need large-vocabulary open-ended dictation rather than command sets
• you need a supported platform other than linux
• you want a modern neural end-to-end assistant with conversational dialogue
• you need active development and frequent updates

Facets

cli-tool · maturity maintenance

speech-recognition nlp cli json speech-processing cli python offline-speech voice-assistant intent-recognition voice-commands pocketsphinx kaldi deepspeech natural-language-processing command-line automation linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="synesthesiam/voice2json")