skills.rest
p8n-ai
p8n-aiOFFICIAL
Explore all skills by this author →
GitHub

pi-listens

Integrate Sarvam AI speech-to-text and text-to-speech for voice interactions.

2|Updated May 9, 2026
Search Tags:#text-to-speech#user engagement#speech-to-text#voice-first#voice interaction
One-click install
npx skills add https://github.com/p8n-ai/pi-listens --skill pi-listens
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pi-listens
Source: https://github.com/p8n-ai/pi-listens/tree/main/skills/pi-listens
Command: npx skills add https://github.com/p8n-ai/pi-listens --skill pi-listens

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sarvamai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables voice interaction with users, simplifying tasks such as voice input/output, speech-to-text, and text-to-speech, enhancing user engagement and accessibility.

Core Features & Use Cases

  • Voice Output: Speak user-facing text using the configured TTS provider.
  • Voice Input: Stream microphone audio and transcribe user speech using the configured STT provider.
  • Voice Ask: Speak a question, listen, and transcribe the user's answer.
  • Voice Transcribe File: Transcribe existing audio files.
  • Voice Setup Check: Diagnose API key, recorder, player, and voice settings.
  • Use Case: Automate voice interactions in applications, enhancing user experience with voice-first capabilities.

Quick Start

Set up your provider API key and run /voice-init in Pi to initialize the global settings.

Frequently Asked Questions about pi-listens

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add voice interaction to an AI agent using speech-to-text and text-to-speech?▼

You can enable voice interaction by integrating speech-to-text and text-to-speech capabilities. This allows agents to transcribe user speech and vocalize responses, creating a voice-first engagement loop.

Do I need a Sarvam AI API key to transcribe audio files and generate speech?▼

Yes, a Sarvam AI API key is required to utilize the speech-to-text and text-to-speech services. You must configure this key during setup to enable audio transcription and voice output.

Can I use voice input and output to automate clarification loops in applications?▼

Yes, you can automate clarification loops using a voice ask feature. This speaks a question to the user, listens to their microphone audio, and transcribes the answer for the agent.

What is the best way to diagnose speech-to-text and text-to-speech setup issues?▼

Run a voice setup check to diagnose your configuration. This validates your API key, microphone recorder, audio player, and voice settings to ensure voice interaction functions correctly.

How do I initialize voice settings for speech-to-text and TTS integration?▼

Initialize your global voice settings by running the voice initialization command after setting up your provider API key. This configures the speech-to-text and text-to-speech environment.

Related Skills

Explore More Product & Management Skills→
a0972199950a0972199950
1

speech-generator

Generates speech audio from text using the ElevenLabs Text-to-Speech API.

Community
Intermediate
matt-fell-aimatt-fell-ai
1

Voice

Dispatch text-to-speech to an external provider via a speak function and CLI.

Community
Basic
diegosouzapwdiegosouzapw
44.0k

omniroute-tts

Route text-to-speech requests through OmniRoute to generate spoken audio.

Community
Intermediate
lvhuanidlvhuanid

ASR

Transcribe spoken audio into written text using the z-ai-web-dev-sdk.

Community
Intermediate