@agimon-ai/doompi-voice
Client audio capture, host transcription, and autonomous narration for Pi agents.
$ pi install npm:@agimon-ai/doompi-voicePackage Catalog
Extensions, skills, prompt templates, and themes published to npm. Install with pi install npm:<package>. See the package docs for details.
Recently published
@brettinternet/pi-progressCompact passive activity and verification progress for Pi12m agopi-live-codexRealtime gpt-live-1-codex voice frontend for the Pi coding agent12m ago@quintinshaw/pi-dynamic-workflowsClaude-Code-style dynamic workflows for Pi — fan a task out across 100s of subagents with real model routing, token/cost accounting, resume, git-worktree isolation, an interactive /workflows TUI, and a real /deep-research.13m ago@henryqw/pi-herdr-toolsClone, hand off, name, and finish Pi conversations in Herdr, with mergeable side questions.14m ago@aemonge-dev/pi-openspec-gateDeclared-work gate for Pi: accounting at the tool-call boundary — every mutation is exempt-recorded, attributed to a focused change, declared by the human, or blocked with remedies. Never permission; never a renderer; never a prompt. Flow vocabulary is sc15m agopi-weaveLocal-first Markdown memory and knowledge graph for Pi, OpenCode and Claude Code: preserve decisions, recall sessions, and explore notes with code.17m agopi-dev-flowEnforced feature workflow for Pi: plan → implement → pre-release → release, gated checkpoints, self-improvement reflections, one git worktree per feature, changelog + publish as part of the release24m ago@foliox/transparent-compact-piDeterministic, verbatim-preserving compaction for Pi, with session-backed subagent context recovery.26m ago
All packages
1-35 / 35 (of 5990)
@agimon-ai/po-voice
Client audio capture, host transcription, and autonomous narration for Pi agents.
$ pi install npm:@agimon-ai/po-voicepi-voicekit
Voice in + voice out for Pi CLI — local-only hold-to-talk STT for Chinese and English (21 offline models) plus offline TTS (Kitten Nano, Piper, Kokoro); no audio is uploaded to a remote speech service
$ pi install npm:pi-voicekitprivateer-speak
Voice for Pi coding agents — /speak reads each turn's final answer aloud, /talk records and transcribes voice input into the composer, both through pluggable providers (local OS voices, any OpenAI-compatible endpoint, or a host-registered provider such as
$ pi install npm:privateer-speak@senad-d/micme
Local voice dictation for Pi coding prompts. Press Alt+M, speak, review, send.
$ pi install npm:@senad-d/micme@luxass/pi-voice
Record voice input with /voice, transcribe locally or through an API, and paste it into Pi's composer.
$ pi install npm:@luxass/pi-voice@tychenjiajun/pi-voice
Speech-to-text for the Pi coding agent: press a shortcut and dictate — transcripts land directly in your chat. Local models (Whisper, Parakeet) or any OpenAI-compatible remote ASR endpoint, with compaction-style post-processing that strips fillers.
$ pi install npm:@tychenjiajun/pi-voice@codexstar/pi-listen
Voice in + voice out for Pi CLI — hold-to-talk STT (Deepgram or 19 offline models) plus TTS (Kitten Nano, Piper, Kokoro, or Deepgram Aura)
$ pi install npm:@codexstar/pi-listenpi-voice-stt
Provider-agnostic speech-to-text for Pi, with interactive voice dictation and audio file transcription.
$ pi install npm:pi-voice-stt@arvoretech/pi-elevenlabs-stt
PI extension for push-to-talk speech-to-text using the ElevenLabs Scribe API
$ pi install npm:@arvoretech/pi-elevenlabs-stt@igpauli/pi-sano-tts
Batteries-included local multilingual MoE Text-to-Speech with acoustic classifier, audible calibration testing, router-in-the-weights, and calibrated LoRA personas for Pi
$ pi install npm:@igpauli/pi-sano-ttspi-harness-whatsapp
Talk to Pi from WhatsApp: images, files and optional voice notes in and out, automatic replies, group chats, poll menus to control Pi.
$ pi install npm:pi-harness-whatsapp@xynogen/pix-voice
Provider-neutral speech-to-text and text-to-speech tools for Pi
$ pi install npm:@xynogen/pix-voice@sfgartland/better-pi-voice
Streaming voice input for pi: Deepgram (nova-3, repo-aware keyterms) or local Parakeet, with Claude-Code-style recovery so speech is never lost.
$ pi install npm:@sfgartland/better-pi-voicepi-live-codex
Realtime gpt-live-1-codex voice frontend for the Pi coding agent
$ pi install npm:pi-live-codex@codexstar/pi-pompom
Pi-Pompom — A 3D raymarched virtual pet with voice, ambient weather sounds, AI side chat, agent tracking, and 23 layered sound effects for Pi CLI
$ pi install npm:@codexstar/pi-pompomgentle-voice
Local voice conversation extension for Pi Coding Agent and Gentle Shell (STT/TTS).
$ pi install npm:gentle-voicejianying-subtitle
CLI tool to transcribe audio/video using JianYing (CapCut) free ASR API
$ pi install npm:jianying-subtitle@benjaminjamesxyz/pi-speak
Real-time neural TTS for the Pi coding agent — speaks assistant responses as they stream, powered by a Rust daemon running Kokoro-82M in-process.
$ pi install npm:@benjaminjamesxyz/pi-speak@maheidem/pi-audio-transcribe
Pi extension: transcribe audio with oMLX STT (Qwen3-ASR), validate the speech, and persist a JSON transcript sidecar beside each audio file.
$ pi install npm:@maheidem/pi-audio-transcribe@qmahyar/pi-9router
Connect pi to 9Router — multi-provider chat models plus image, speech, search, and fetch tools
$ pi install npm:@qmahyar/pi-9router@artale/pi-voice
Voice input for Pi. Multi-provider STT with Deepgram streaming, Groq Whisper, OpenAI Whisper. 56+ languages.
$ pi install npm:@artale/pi-voicepi-voice-input
Press Ctrl+Shift+R to dictate prompts into Pi using VolcEngine ASR
$ pi install npm:pi-voice-inputpicrophone
On-device dictation + text-to-speech bridge for the pi coding agent (macOS; Windows coming soon).
$ pi install npm:picrophone@speclip/pi-speech
Workspace-safe local ASR/TTS, optional cloud speech, retries, billing estimates, and generation records for Pi
$ pi install npm:@speclip/pi-speech@jay-zod/speak
Convert text to speech using Chatterbox TTS on Apple Silicon
$ pi install npm:@jay-zod/speak@benjaminjamesxyz/pi-voice-input
Voice-to-prompt extension for pi: mic capture -> neural denoising (clean_voice_dsp) + local Whisper transcription
$ pi install npm:@benjaminjamesxyz/pi-voice-inputpi-whisper-voice
Minimal hold-SPACE voice input for Pi using an OpenAI-compatible Whisper/STT endpoint.
$ pi install npm:pi-whisper-voice