skills.rest
Nackalalalong
NackalalalongCOMMUNITY
Explore all skills by this author →
GitHub

Speaches Integration

Connect to a self-hosted Speaches server for ASR, TTS, VAD, and chat APIs.

Updated Apr 11, 2026
Search Tags:#integration#streaming#realtime#tts#self-hosted#asr#speaches
One-click install
npx skills add https://github.com/Nackalalalong/voicebot-rs --skill speaches-integration
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Speaches Integration
Source: https://github.com/Nackalalalong/voicebot-rs/tree/main/skills/speaches
Command: npx skills add https://github.com/Nackalalalong/voicebot-rs --skill speaches-integration

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Integrates with a self-hosted Speaches server to enable high-quality ASR (faster-whisper), TTS (Kokoro/Piper), VAD (Silero), and the OpenAI-compatible Chat + Realtime API.

Core Features & Use Cases

  • Connect to a Speaches server over HTTP for ASR, TTS, and chat APIs.
  • Use WebSocket real-time streaming for low-latency audio and transcripts.
  • Manage timeouts, retries, and API keys centrally to ensure robust operation.
  • Use-case: local AI assistants that transcribe speech, synthesize speech, and chat in real time within an isolated network.

Quick Start

Start by connecting to your local Speaches server and begin streaming audio through the integration.

Frequently Asked Questions about Speaches Integration

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

FAQPage Schema
How do I integrate a self-hosted Speaches server for local ASR and TTS?▼

To integrate a self-hosted Speaches server for local ASR and TTS, connect over HTTP or WebSocket to a configurable base URL, enabling faster-whisper transcription and Kokoro/Piper speech synthesis with optional API key support.

Does Speaches integration support real-time audio streaming over WebSocket?▼

Yes, Speaches integration supports real-time audio streaming over WebSocket, providing low-latency audio and transcript processing for local AI assistants through the OpenAI-compatible Realtime API.

How do I configure timeouts and retries for self-hosted speech recognition APIs?▼

You can configure timeouts and retries centrally for self-hosted speech recognition APIs by setting endpoint timeouts and robust retry behavior within the Speaches integration, ensuring reliable operation during network fluctuations.

Can I use the OpenAI-compatible Chat API with my local Speaches deployment?▼

Yes, you can use the OpenAI-compatible Chat API with your local Speaches deployment by managing API keys centrally and routing requests through the configurable base URL to handle chat interactions.

What is VAD and how does Silero voice activity detection work with Speaches?▼

VAD, or voice activity detection, identifies speech segments in audio; Silero VAD works with Speaches by processing AudioFrame inputs to isolate spoken audio before passing it to the ASR transcription engine.

How do I handle AudioFrame input and output for local TTS and ASR processing?▼

To handle AudioFrame input and output for local TTS and ASR processing, the Speaches integration manages AudioFrame transmission over HTTP and WebSocket connections, ensuring proper audio data synchronization for real-time streaming.

Related Skills

Explore More Software Engineering Skills→
faramirezsfaramirezs

siyuan

Automate SiYuan block and document operations via HTTP API using curl.

Community
Intermediate
Nidhi786sharmaNidhi786sharma
3

Restaurant Bot

Handle restaurant menu inquiries, offers, and orders via Watson Assistant.

Community
Intermediate
bomberoxenviosdosruedasbomberoxenviosdosruedas

agency-voice-ai-integration-engineer

Build speech transcription pipelines using Whisper models and cloud ASR services.

Community
Advanced
mofa-orgmofa-org
11

voice

Transcribe audio to text and generate expressive speech on-device via ominix-api.

Official
Advanced