jargo

README

A WebRTC-native, audio-first conversational-AI framework for Go.

---

jargo builds real-time voice agents in Go: audio in over WebRTC, a streaming transcription → reasoning → speech pipeline with turn-taking and barge-in, and audio back out — over RTVI so existing clients interoperate.

Status: early work in progress. APIs are unstable and will change.

Why?

Pipecat is great, and jargo is a port of it — the architecture and many design decisions are Pipecat's.

Python might not be the way

This port exists for one reason: I'd rather not run a voice agent on Python.

Python is the right tool when you need the AI/data-science ecosystem. A real-time voice server doesn't: the models run as services or as ONNX, and what's left is plumbing — audio framing, WebRTC, concurrency, and shipping a binary. For that, Go is a better fit: one static binary to deploy, low and predictable memory, fast startup, and real concurrency for many simultaneous sessions without a GIL. The heavy numerics stay where they belong (the ONNX Runtime, the remote services), so giving up Python costs little here. See the benchmarks for the honest performance picture.

No Daily, no lock-in

jargo stays on plain, standard WebRTC via Pion — no Daily, no hosted transport, no proprietary SDK or cloud to sign up for. You ship one binary, the browser connects with vanilla WebRTC, and RTVI rides the data channel. Keeping the transport open and self-hosted is a deliberate goal, not an afterthought.

Features

• WebRTC, pure Go (Pion) — audio in and out of the browser.
• Opus, pure Go encode + decode via pion/opus; C libopus optional with -tags libopus.
• Resampling, pure Go via go-resample; libsoxr optional with -tags libsoxr.
• Streaming voice pipeline: STT → LLM → TTS, with prompt caching.
• Speech-to-speech: single-model voice agents (OpenAI Realtime, Gemini Live, AWS Nova Sonic).
• Turn-taking & barge-in: Silero VAD + Smart Turn v3, local ONNX.
• Telephony (optional): inbound/outbound phone calls over Twilio Media Streams.
• User-idle watchdog: re-engage or hang up when the caller goes silent.
• RTVI data channel — works with existing RTVI clients.
• Pluggable services: swap any STT/LLM/TTS behind a small interface.
• Concurrent by design: independent processors; interruptions are frames.

Providers

Pick any per category; each is a small Config + constructor.

• STT: Deepgram, AssemblyAI, Gladia, Speechmatics, Soniox, Whisper (OpenAI/Groq/local), Azure.
• LLM: Anthropic (direct + Bedrock), OpenAI, Google Gemini, Groq, Together, Fireworks, DeepSeek, Cerebras, Perplexity, OpenRouter, xAI, Ollama, NVIDIA, Mistral, Nebius, SambaNova, Qwen, Azure OpenAI.
• TTS: ElevenLabs, Cartesia, Rime, LMNT, Kokoro, Piper, Deepgram, OpenAI, Azure, Hume, Fish, MiniMax.
• Speech-to-speech: OpenAI Realtime, Gemini Live, AWS Nova Sonic.
• Memory: mem0.

Dependencies

The default build is cgo-free — CGO_ENABLED=0 go build ./... works with no C toolchain. Two native runtimes are still used, but bound through purego and loaded at run time, so they need their shared library present at runtime and nothing at build time:

• ONNX Runtime — VAD + end-of-turn detection (JARGO_ONNXRUNTIME_LIB).
• RNNoise — optional input noise reduction (JARGO_RNNOISE_LIB).

Opus and resampling are pure Go by default; the C libopus (-tags libopus) and libsoxr (-tags libsoxr) are the only cgo in the tree, and both are optional. The base images bundle all of them.

Usage

go get github.com/gojargo/jargo

A bot is an STT → LLM → TTS pipeline over a WebRTC transport. The heart of it:

stt := openai.NewSTT(openai.STTConfig{APIKey: key, SampleRate: opus.SampleRate})
llm := openai.NewLLM(openai.LLMConfig{APIKey: key})
tts := openai.NewTTS(openai.TTSConfig{APIKey: key})

t := pionrtc.NewTransport(conn, transport.DefaultParams())
agg := aggregators.New(frames.NewLLMContext("You are a helpful voice assistant."))

task := pipeline.NewTask(pipeline.New(
	t.Input(), stt, agg.User(), llm, tts, t.Output(), agg.Assistant(),
), pipeline.TaskParams{})
task.Run(ctx)

examples/voice/openai is that pipeline as a complete server (WebRTC signaling, VAD/turn-taking, barge-in).

Run it in Docker — build on the gojargo/jargo-build base and ship on the distroless gojargo/jargo runtime (it bundles the ONNX Runtime), then:

docker run --rm -p 8080:8080 -e OPENAI_API_KEY=$OPENAI_API_KEY my-bot

See Deploy with Docker for the Dockerfile and the Quickstart for the full setup.

Examples

Runnable bots live in examples/:

• echo — hear yourself back, no API keys.
• voicebot — the full voice agent (STT → LLM → TTS over WebRTC) with turn-taking, long-term memory, and tracing.
• voice/ — one headless backend per provider, each wiring its STT/LLM/TTS explicitly and exposing the WebRTC /offer endpoint (no web UI). Run with go run ./examples/voice/<provider> (e.g. deepgram, cartesia, openai) and drive it from a browser client — the nextjs-voicebot in jargo-client-react.
• twiliobot — a phone agent over Twilio Media Streams, with the idle watchdog.

The fastest way to try them — locally or with Docker — is the Quickstart.

go run ./examples/echo                 # then open http://localhost:8080

Documentation

See docs/index.md for the full documentation.

License & attribution

jargo is a Go port of Pipecat, distributed under the same BSD 2-Clause License. The upstream copyright — Copyright (c) 2024–2026, Daily — is preserved verbatim in LICENSE; see NOTICE for details. jargo is an independent project, not affiliated with or endorsed by Daily.

Documentation

Overview

Package jargo is a framework for building real-time voice and multimodal AI pipelines.