# Patter | Documentation

## Docs

- [Welcome](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/home/index.md): Give your AI agent a phone number. Patter handles telephony, speech-to-text, and text-to-speech so you can focus on your agent.
- [Create a Project](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/quickstart-create.md): Scaffold a runnable Patter voice agent in seconds with the interactive setup wizard — npm create getpatter (TypeScript) or getpatter init (Python).
- [Python SDK](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/home/redirects/python.md): Voice AI SDK for Python
- [TypeScript SDK](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/home/redirects/typescript.md): Voice AI SDK for TypeScript
- [Core Concepts](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/concepts.md): What Patter is, how a voice call flows through it, and the building blocks you'll use
- [OpenClaw](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/integrations/openclaw.md): Give an OpenClaw agent a phone with Patter — connect patter-mcp as an MCP server to place calls, or point Patter consult at one scoped OpenClaw receptionist agent to drive hard turns mid-call without dropping the line.
- [Hermes Agent](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/integrations/hermes.md): Give your Hermes Agent a phone with Patter — make Hermes the voice the caller talks to, connect the Patter MCP server so Hermes can place calls, or let an in-call Patter agent consult Hermes as its brain.
- [Dashboard](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/dev-tools/dashboard.md): Real-time call monitoring dashboard — Vite + React SPA bundled into a single HTML file embedded by both SDKs.
- [Tunneling](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/dev-tools/tunneling.md): Expose your local Patter server to the internet for Twilio webhooks.
- [Production Deployment](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/dev-tools/production-deployment.md): Take a Patter agent from a dev quick-tunnel to a hardened, always-on box: a named Cloudflare tunnel with INGRESS rules, a locked-down dashboard, and a per-client go-live checklist.
- [Python SDK](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/overview.md): Connect AI agents to phone numbers with 4 lines of Python.
- [Quickstart](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/quickstart.md): Give your AI agent a phone number in four lines of Python.
- [Configuration](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/configuration.md): All Patter constructor parameters for local mode.
- [Agents](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/agents.md): Configure voice AI agents with system prompts, tools, engines, and guardrails.
- [Carrier](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/carrier.md): Telephony providers: Twilio, Telnyx, and Plivo.
- [Engines](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/engines.md): End-to-end speech-to-speech runtimes (OpenAI Realtime, OpenAI Realtime 2, ElevenLabs ConvAI).
- [OpenAI Realtime](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/openai-realtime.md): Models, voices, transcription, and reasoning effort for the OpenAI Realtime engine.
- [OpenAI Realtime 2 (GA)](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/openai-realtime-2.md): GA Realtime API engine — separate adapter that speaks the new session.update wire shape required by gpt-realtime-2.
- [Gemini Live](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/gemini-live.md): Google Gemini Live native-audio realtime engine — alternative to OpenAI Realtime.
- [Ultravox Realtime](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/ultravox-realtime.md): Ultravox managed-agent realtime engine — pure WebSocket, no vendor SDK.
- [ElevenLabs ConvAI](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/elevenlabs-convai.md): End-to-end speech-to-speech engine backed by an ElevenLabs-hosted Conversational AI agent.
- [xAI Realtime](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/xai-realtime.md): xAI Grok Voice Agent — OpenAI-Realtime-GA-compatible speech-to-speech engine with reasoning, server-side tools, and pronunciation control.
- [Inworld Realtime](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/inworld-realtime.md): Inworld's OpenAI-Realtime-compatible speech-to-speech engine — one WebSocket for STT, LLM, and TTS.
- [STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/stt.md): Speech-to-text providers supported by Patter.
- [AssemblyAI STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/assemblyai.md): Universal Streaming speech-to-text via AssemblyAI's v3 WebSocket API.
- [Cartesia](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/cartesia.md): Cartesia STT (ink-whisper) and TTS (sonic) providers.
- [Deepgram STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/deepgram.md): Streaming speech-to-text via Deepgram's v1 /listen WebSocket API.
- [Whisper STT (OpenAI)](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/whisper.md): OpenAI Whisper REST and GPT-4o transcribe family for Patter pipeline mode.
- [Soniox STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/soniox.md): Soniox real-time streaming speech-to-text for Patter pipeline mode.
- [Speechmatics STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/speechmatics.md): Speechmatics real-time speech-to-text via the official Voice Agent SDK.
- [Telnyx STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/telnyx-stt.md): Streaming speech-to-text bundled with your Telnyx telephony plan — single bill, on-network audio.
- [xAI STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/xai-stt.md): xAI (Grok) real-time streaming speech-to-text plus a one-shot batch transcription helper for Patter pipeline mode.
- [Fish Audio STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/fish-audio-stt.md): Batch transcription via Fish Audio's ASR endpoint — one vendor for both directions of the call, at $0.36 per audio hour.
- [LLM](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/llm.md): Pick an LLM provider the same way you pick STT and TTS.
- [Anthropic](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/anthropic.md): Anthropic Claude LLM provider — Messages API with streaming, tool use, and prompt caching.
- [Cerebras](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/cerebras.md): Cerebras LLM provider — OpenAI-compatible Inference API with WSE-3 throughput.
- [Google](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/google.md): Google Gemini LLM provider — Developer API or Vertex AI, streaming with function calling.
- [Groq](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/groq.md): Groq LLM provider — hardware-accelerated Llama inference via OpenAI-compatible Chat Completions.
- [TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/tts.md): Text-to-speech providers supported by Patter.
- [ElevenLabs TTS (REST)](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/elevenlabs-tts.md): Streaming HTTP/REST TTS adapter for ElevenLabs voices. Simpler and more network-tolerant than the WebSocket variant.
- [ElevenLabs WebSocket](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/elevenlabs-websocket.md): Opt-in low-latency WebSocket variant of ElevenLabsTTS. Drop-in API, saves ~50 ms per utterance.
- [Rime TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/rime.md): Arcana and Mist model families via Rime's HTTP endpoint.
- [LMNT TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/lmnt.md): Blizzard and Aurora TTS models via the LMNT HTTP API.
- [OpenAI TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/openai-tts.md): tts-1, tts-1-hd, and gpt-4o-mini-tts via OpenAI's HTTP TTS endpoint.
- [Cartesia TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/cartesia-tts.md): Sonic-1, Sonic-2, and Sonic-3 voice synthesis via Cartesia's HTTP bytes endpoint.
- [Inworld TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/inworld.md): TTS-2 (sub-200 ms TTFA, 100+ languages, natural-language voice steering) and the TTS-1.5 family via Inworld's HTTP NDJSON streaming endpoint.
- [Telnyx TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/telnyx-tts.md): Streaming text-to-speech bundled with your Telnyx telephony plan — single bill, on-network audio.
- [xAI TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/xai-tts.md): xAI (Grok) text-to-speech — expressive voices, inline speech tags, and telephony-native output over the one-shot /tts bytes endpoint.
- [Fish Audio TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/fish-audio-tts.md): S2.1-Pro (83 languages, bracket expression control, multi-speaker) and S2-Pro (~100 ms time-to-first-audio) over Fish Audio's HTTP streaming and WebSocket endpoints.
- [Silero VAD](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/silero-vad.md): ONNX-backed voice activity detection for fast, accurate barge-in in pipeline mode.
- [Krisp Filter](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/krisp-filter.md): Proprietary Krisp VIVA noise / echo suppression as a Patter AudioFilter.
- [DeepFilterNet](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/providers/deepfilternet-filter.md): Open-source DeepFilterNet3 noise suppression as a Patter AudioFilter.
- [Tools & Function Calling](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/tools.md): Let your voice agent call APIs, query databases, and take actions during a conversation.
- [Skills](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/skills.md): Give the primary agent on-demand capabilities it activates inline — progressive disclosure, no sub-agent latency.
- [Consult your agent](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/consult.md): Let an in-call Patter agent escalate to your own back-office agent over HTTP — the dispatch + consult pattern.
- [Guardrails](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/guardrails.md): Filter and control AI responses before they reach the caller.
- [Events](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/events.md): React to call lifecycle events with async callbacks.
- [Advanced Features](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/features.md): Recording, AMD, DTMF, call transfer, barge-in, and more.
- [Metrics & Cost Tracking](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/metrics.md): Per-call cost breakdown, latency analytics, and real-time metrics.
- [Dashboard](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/dashboard.md): Embedded web dashboard for real-time call monitoring, latency, and cost analytics.
- [Call logging](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/call-logging.md): Opt-in per-call filesystem logs: metadata, transcripts, and operational events.
- [Tracing (OpenTelemetry)](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/tracing.md): Opt-in OpenTelemetry tracing for STT, LLM, TTS, and tool calls.
- [Anonymous telemetry](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/telemetry.md): What Patter's opt-out usage telemetry collects, and how to disable it.
- [PatterTool — phone as a tool](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/patter-tool.md): Wrap a Patter instance so external agents (LangChain, OpenAI Assistants, Anthropic Claude, Hermes, MCP) can place real phone calls as a single tool invocation.
- [MCP — Model Context Protocol](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/mcp.md): Plug a Patter agent into MCP servers (Google Workspace, PayPal, Postgres, GitHub, …) without writing wrapper handlers. Tools are discovered at call start and dispatched through the MCP client transparently.
- [Test Mode](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/test-mode.md): Interactive terminal testing for voice agents without telephony, STT, or TTS.
- [Local Mode](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/local-mode.md): Run a fully self-hosted voice AI server with your own telephony and AI provider keys.
- [API Reference](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/python-sdk/reference.md): Complete reference for all classes, methods, parameters, and types in the Patter Python SDK.
- [TypeScript SDK](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/overview.md): Connect AI agents to phone numbers with 4 lines of TypeScript.
- [Quickstart](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/quickstart.md): Give your AI agent a phone number in four lines of TypeScript.
- [Configuration](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/configuration.md): Constructor options for local mode.
- [Agents](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/agents.md): Define your agent's voice, model, tools, and behavior for phone calls.
- [Carrier](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/carrier.md): Telephony providers: Twilio, Telnyx, and Plivo.
- [Engines](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/engines.md): End-to-end speech-to-speech runtimes (OpenAI Realtime, ElevenLabs ConvAI).
- [OpenAI Realtime](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/openai-realtime.md): Models, voices, transcription, and reasoning effort for the OpenAI Realtime engine.
- [OpenAI Realtime 2 (GA)](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/openai-realtime-2.md): GA Realtime API engine — separate adapter that speaks the new session.update wire shape required by gpt-realtime-2.
- [Gemini Live](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/gemini-live.md): Google Gemini Live native-audio realtime engine — alternative to OpenAI Realtime.
- [Ultravox Realtime](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/ultravox-realtime.md): Ultravox managed-agent realtime engine — pure WebSocket, no vendor SDK.
- [ElevenLabs ConvAI](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/elevenlabs-convai.md): End-to-end speech-to-speech engine backed by an ElevenLabs-hosted Conversational AI agent.
- [xAI Realtime](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/xai-realtime.md): xAI Grok Voice Agent — OpenAI-Realtime-GA-compatible speech-to-speech engine with reasoning, server-side tools, and pronunciation control.
- [STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/stt.md): Speech-to-text providers supported by Patter.
- [AssemblyAI STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/assemblyai.md): Universal Streaming speech-to-text via AssemblyAI's v3 WebSocket API.
- [Cartesia STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/cartesia.md): Streaming speech-to-text via Cartesia's ink-whisper model.
- [Deepgram STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/deepgram.md): Streaming speech-to-text via Deepgram's v1 /listen WebSocket API.
- [Whisper STT (OpenAI)](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/whisper.md): OpenAI Whisper REST and GPT-4o transcribe family for Patter pipeline mode.
- [Soniox STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/soniox.md): Soniox real-time streaming speech-to-text for Patter pipeline mode.
- [Speechmatics STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/speechmatics.md): Speechmatics real-time speech-to-text — Python-only today; TypeScript port pending.
- [Telnyx STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/telnyx-stt.md): Streaming speech-to-text bundled with your Telnyx telephony plan — single bill, on-network audio.
- [xAI STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/xai-stt.md): xAI (Grok) real-time streaming speech-to-text plus a one-shot batch transcription helper for Patter pipeline mode.
- [Fish Audio STT](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/fish-audio-stt.md): Batch transcription via Fish Audio's ASR endpoint — one vendor for both directions of the call, at $0.36 per audio hour.
- [LLM](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/llm.md): Pick an LLM provider the same way you pick STT and TTS.
- [Anthropic](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/anthropic.md): Anthropic Claude LLM provider — Messages API with streaming, tool use, and prompt caching.
- [Cerebras](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/cerebras.md): Cerebras LLM provider — OpenAI-compatible Inference API with WSE-3 throughput.
- [Google](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/google.md): Google Gemini LLM provider — Developer API streaming with function calling.
- [Groq](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/groq.md): Groq LLM provider — hardware-accelerated Llama inference via OpenAI-compatible Chat Completions.
- [TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/tts.md): Text-to-speech providers supported by Patter.
- [ElevenLabs TTS (REST)](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/elevenlabs-tts.md): Streaming HTTP/REST TTS adapter for ElevenLabs voices. Simpler and more network-tolerant than the WebSocket variant.
- [ElevenLabs WebSocket TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/elevenlabs-websocket.md): Opt-in WebSocket variant of ElevenLabsTTS that trims HTTP setup latency.
- [Rime TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/rime.md): Arcana and Mist model families via Rime's HTTP endpoint.
- [LMNT TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/lmnt.md): Blizzard and Aurora TTS models via the LMNT HTTP API.
- [OpenAI TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/openai-tts.md): tts-1, tts-1-hd, and gpt-4o-mini-tts via OpenAI's HTTP TTS endpoint.
- [Cartesia TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/cartesia-tts.md): Sonic-1, Sonic-2, and Sonic-3 voice synthesis via Cartesia's HTTP bytes endpoint.
- [Inworld TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/inworld.md): TTS-2 (sub-200 ms TTFA, 100+ languages, natural-language voice steering) and the TTS-1.5 family via Inworld's HTTP NDJSON streaming endpoint.
- [Telnyx TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/telnyx-tts.md): Streaming text-to-speech bundled with your Telnyx telephony plan — single bill, on-network audio.
- [xAI TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/xai-tts.md): xAI (Grok) text-to-speech — expressive voices, inline speech tags, and telephony-native output over the one-shot /tts bytes endpoint.
- [Fish Audio TTS](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/fish-audio-tts.md): S2.1-Pro (83 languages, bracket expression control, multi-speaker) and S2-Pro (~100 ms time-to-first-audio) over Fish Audio's HTTP streaming and WebSocket endpoints.
- [Silero VAD](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/silero-vad.md): ONNX-backed voice activity detection for fast, accurate barge-in in pipeline mode.
- [Krisp Filter](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/krisp-filter.md): Proprietary Krisp VIVA noise / echo suppression as a Patter AudioFilter.
- [DeepFilterNet](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/providers/deepfilternet-filter.md): Open-source DeepFilterNet3 noise suppression as a Patter AudioFilter.
- [Tools](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/tools.md): Function calling, webhook tools, and system tools for voice agents.
- [Skills](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/skills.md): Give the primary agent on-demand capabilities it activates inline — progressive disclosure, no sub-agent latency.
- [Consult your agent](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/consult.md): Let an in-call Patter agent escalate to your own back-office agent over HTTP — the dispatch + consult pattern.
- [Guardrails](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/guardrails.md): Filter and control AI agent responses before they reach callers.
- [Events](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/events.md): React to call lifecycle events with typed callbacks.
- [Advanced Features](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/features.md): Recording, AMD, DTMF, call transfer, barge-in, variables, and conversation history.
- [Metrics & Cost Tracking](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/metrics.md): Per-call cost breakdown, latency analytics, and real-time metrics.
- [Dashboard](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/dashboard.md): Embedded web dashboard for real-time call monitoring, latency, and cost analytics.
- [Call logging](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/call-logging.md): Opt-in per-call filesystem logs: metadata, transcripts, and operational events.
- [Tracing (OpenTelemetry)](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/tracing.md): Opt-in OpenTelemetry tracing for STT, LLM, TTS, endpointing, barge-in, and tool calls.
- [PatterTool — phone as a tool](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/patter-tool.md): Wrap a Patter instance so external agents (LangChain, OpenAI Assistants, Anthropic Claude, Hermes, MCP) can place real phone calls as a single tool invocation.
- [MCP — Model Context Protocol](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/mcp.md): Plug a Patter agent into MCP servers (Google Workspace, PayPal, Postgres, GitHub, …) without writing wrapper handlers. Tools are discovered at call start and dispatched through the MCP client transparently.
- [Test Mode](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/test-mode.md): Test your agent in the terminal without telephony, STT, or TTS.
- [Local Mode](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/local-mode.md): Self-hosted embedded server, webhook endpoints, and WebSocket streams.
- [API Reference](https://patter-06b046ce-feat-py-inworld-realtime.mintlify.site/typescript-sdk/reference.md): Complete type definitions, interfaces, error classes, and exports.