Show HN: Brisvox – a Rust engine for real-time voice agents, phone and browser A developer released Brisvox, an open-source Rust engine for real-time voice agents on phone and browser, claiming it carried 250 concurrent calls within a latency SLO on a single 4 vCPU / 4 GB container versus 1 for Pipecat 1.12.0. In the same benchmark, Brisvox reached 430 calls without a failed call or lost turn against 10 for Pipecat, and at 8 vCPU / 8 GB it scaled to 470 and 780 calls while Pipecat stayed at 10. On real providers (Deepgram STT, an OpenAI-compatible LLM, Deepgram Aura voice) across 5 concurrent calls and 100 turns, Brisvox reported median voice-to-voice latency of 1.85 s versus 1.97 s for Pipecat and p95 of 2.88 s versus 4.35 s. A Rust engine for real-time voice agents: phone calls and browser sessions where a caller talks, the agent listens, thinks an LLM, with tools and answers, and the caller can interrupt at any moment. Open source, one process, hundreds of isolated calls per container. Website: brisvox.com https://brisvox.com · Install install · Try it without keys try-it-without-keys · Quickstart quickstart · Comparison brisvox-vs-livekit-agents-vs-pipecat · Features features · For AI coding agents for-ai-coding-agents · Docs: the book https://github.com/bilal07karadeniz/brisvox/blob/main/book/src/introduction.md · Discussions https://github.com/bilal07karadeniz/brisvox/discussions · License license Built to beat Pipecat on three axes with the same speech and language providers: latency, density and correctness. - Density. Every call through each system's own provider client code Deepgram live STT, an OpenAI-compatible LLM and Deepgram Aura over TLS, against protocol-faithful fake servers with the real Silero VAD and Smart Turn models on every call: one 4 vCPU / 4 GB cloud container carried 250 concurrent calls within the latency SLO and 430 without a failed call or a lost turn, against 1 and 10 for Pipecat 1.12.0. At 8 vCPU / 8 GB brisvox nearly doubled to 470 and 780 ; Pipecat stayed at 10 . At its maximum brisvox used about 1.8 MB of memory and 0.007 cores per call, Pipecat about 240 MB and 0.14 cores. Each call is an isolated session; a panic or a provider failure in one cannot touch another. - Latency. The engine's own added time is tens of microseconds per stage 0.089 ms at p95 from end of turn to the LLM request, budget 3 ms . On real providers Deepgram, OpenRouter pinned to one upstream, Deepgram Aura voice , 5 concurrent calls, 100 turns per system, the median voice-to-voice was 1.85 s against 1.97 s for Pipecat and the p95 2.88 s against 4.35 s . The STT final arrived earlier through brisvox its Finalize runs at the VAD stop instead of waiting for the provider's own endpointing; the two systems' timers are not measured from the same point, so this is not a share of the gap ; the LLM's first token took about the same time on both. Pipecat sent more than one LLM request in 56 of 100 turns mostly the first turn of a call , which is where its tail comes from; the cause was not investigated it is consistent with a turn ended at a pause inside the utterance . An earlier run with Cartesia, one call at a time and 30 turns, gave 1.69 s against 2.03 s. Connections are prewarmed, the LLM can start speculatively, and the first clause of the answer goes to the voice after one word. - Correctness. Every user turn is a numbered epoch and stale frames are dropped everywhere; after a barge-in the LLM context holds only the text that was actually played; side-effect tools never run speculatively and never run twice for one call id and an identical repeat in the same turn is refused . The exact scope, and the idempotency key to add for "once per order, ever", is in docs/TOOLS.md https://github.com/bilal07karadeniz/brisvox/blob/main/docs/TOOLS.md what-never-twice-covers . All of it is proven by deterministic, paused-clock simulation. The same SLO for both p95 voice-to-voice at most 1110 ms: the fake providers' own 860 ms plus 250 ms , three runs each on a fresh container, one system at a time, on one CPU model AMD EPYC 9655P; deployments the cloud placed on other CPUs were redeployed with the container limits checked in its own samples. On these cores a single Pipecat call already sits near the limit p95 about 1.05 to 1.1 s at one call, about 200 ms above the providers' floor, against 10 to 30 ms for brisvox , so its SLO number is decided by per-turn latency more than by load. The next chart drops the latency limit and shows how many calls each system holds without failing: Pipecat one worker process per vCPU, Silero and Smart Turn loaded in each runs out of memory at 20 calls in 4 GB: workers are killed and their calls drop. With 8 GB it lost turns at 20 calls in two of three runs no response ; the third held 20 and reached the 8 GB limit at 30, where calls dropped. So the extra cores and memory did not raise its median. brisvox is bound by CPU: twice the container gave about 1.9 times the calls. Latency stays at the providers' floor until a system runs out of CPU or memory, then crosses the SLO within a step or two: the number that matters is where that happens. Both systems ran the same agent file against the same real providers and models Deepgram nova-3, OpenRouter openai/gpt-6-luna with reasoning effort none , pinned to OpenRouter's openai upstream without fallbacks and checked on every response that streamed Pipecat's cancelled requests never reported one , Deepgram Aura aura-2-thalia-en , with 5 concurrent calls, 10 blocks of 10 turns per system, strictly alternating b1 p1 b2 p2 ... , so both saw the same provider conditions. The LLM provider's own variance is still as large as the median difference 126 ms : the LLM first token is 931 ms for brisvox and 889 ms for Pipecat at p50. The tail differs more than the median because Pipecat sent a second or third LLM request in about half of the turns here one call at a time it was 5 of 30 . One setting is not equal: the same nominal 100 ms silence before the VAD stop is 3 Silero windows 96 ms in Pipecat and 4 128 ms in brisvox, so Pipecat decides about 32 ms earlier at every turn end faster when the turn really ended, and a candidate for its extra mid-utterance turn ends ; the breakdown by stage, the routing check, this mismatch and the earlier Cartesia runs are in the "Live comparison with real providers" section of docs/LATENCY.md https://github.com/bilal07karadeniz/brisvox/blob/main/docs/LATENCY.md . - Capacity and memory are cloud runs of 2026-10-16/17: Linux containers on AMD EPYC 9655P Zen 5 limited to 4 vCPU / 4 GB and 8 vCPU / 8 GB, release builds, one system at a time. Every call goes through each system's own provider clients brisvox's Rust adapters; Pipecat's DeepgramSTTService , OpenAILLMService and DeepgramTTSService to fake providers that speak the real Deepgram and OpenAI-compatible protocols over TLS with fixed latencies STT final 150 ms after 300 ms of endpointing, LLM first token 350 ms, TTS first audio 150 ms; bench/fake providers https://github.com/bilal07karadeniz/brisvox/blob/main/bench/fake providers/README.md , in a container of their own, like the load generator. So the numbers include the provider client code, TLS and both models, not the providers' own variance. The Pipecat side is bench/pipecat baseline : a Pipecat 1.12.0 bot speaking the same websocket protocol with the same agent file, measured by the same client with the same definition of voice-to-voice. brisvox's admission control was off for the ramp; in production it refuses calls past its capacity instead of degrading the running ones. LiveKit Agents was not part of this run. - Memory is PSS proportional set size: a page shared by several processes is split between them summed over the server container's processes, from its cgroup samples every 2 s. - The same comparison runs locally with PROVIDERS=fakes MODELS=1 bench/capacity linux.sh Docker containers with the same limits . The Smart Turn model is memory-bandwidth heavy about 200 MB of memory traffic per analysis , so on a desktop with little memory bandwidth it can stop brisvox from scaling with cores before the CPU does; the cloud host above does not. - Live voice-to-voice is Windows on a shared development machine over the public internet, one evening 100 turns per system, 5 concurrent calls, alternating blocks; Cartesia's plan allows only 2 concurrent generations, hence the Aura voice ; absolute numbers carry noise. Engine overhead is the Windows run over mocks. - Every number is in a committed file under bench/results/ https://github.com/bilal07karadeniz/brisvox/blob/main/bench/results/README.md the file starts with the command that produced it ; the charts are generated from those files by python3 scripts/gen charts.py and checked for staleness by the quality gate. Definitions and more results load simulation, speculation, Windows capacity : the book's Benchmark results https://github.com/bilal07karadeniz/brisvox/blob/main/book/src/benchmarks.md and docs/LATENCY.md https://github.com/bilal07karadeniz/brisvox/blob/main/docs/LATENCY.md . Two kinds of rows. Measured rows come from this repository's own benchmark harness files named in the last column; the table is generated from them ; "not measured" means this repository has no such run for that system yet. Documented rows are what each project's own documentation and repository say, fetched 2026-10-14, not benchmarks; the bracketed tags are source ids listed in docs/research/frameworks-2026-10-14.md https://github.com/bilal07karadeniz/brisvox/blob/main/docs/research/frameworks-2026-10-14.md , where every fact carries its URL and what is inferred or not stated is marked as such. | Measured here | brisvox | LiveKit Agents | Pipecat 1.12 | Source | |---|---|---|---|---| | Concurrent calls within the latency SLO p95 voice-to-voice at most 1110 ms , 4 vCPU / 4 GB median, runs in brackets | 250 260, 250, 220 | not measured | 1 1, 1, 0 | bench/results/capacity- -cloud-4c-linux- | | Most concurrent calls with no failed call and no lost turn any latency , 4 vCPU / 4 GB | 430 430, 480, 400 | not measured | 10 10, 10, 10 | bench/results/capacity- -cloud-4c-max-linux- | | Server memory at that maximum, 4 vCPU / 4 GB PSS summed over the container's processes | 753 MB at 430 calls | not measured | 2.4 GB at 10 calls | same files | | Concurrent calls within the latency SLO p95 voice-to-voice at most 1110 ms , 8 vCPU / 8 GB median, runs in brackets | 470 480, 460, 470 | not measured | 10 10, 5, 10 | bench/results/capacity- -cloud-8c-linux- | | Most concurrent calls with no failed call and no lost turn any latency , 8 vCPU / 8 GB | 780 740, 780, 800 | not measured | 10 10, 20, 10 | bench/results/capacity- -cloud-8c-max-linux- | | Server memory at that maximum, 8 vCPU / 8 GB PSS summed over the container's processes | 1.3 GB at 780 calls | not measured | 3.3 GB at 10 calls | same files | | Per call at that maximum, 4 vCPU / 4 GB: memory and CPU idle baseline included | 1.8 MB, 0.007 cores | not measured | 239.9 MB, 0.137 cores | same files | | Voice-to-voice on real providers, English, p50 / p95 5 concurrent calls, 100 turns, Deepgram Aura voice; Windows, public internet | 1.85 s / 2.88 s 100 turns | not measured | 1.97 s / 4.35 s 100 turns | bench/results/v2v-live- -windows- | | Documented 2026-10-14 | brisvox | LiveKit Agents | Pipecat | |---|---|---|---| | Language | Rust engine; your agent in Python or TypeScript SDKs on PyPI and npm or in Rust | Python livekit-agents 1.8.7 ; Node.js in a separate repo L2 L5 | Python pipecat-ai 1.12.0 P2 P4 | | License | Apache-2.0 or MIT | Apache-2.0; the turn-detector text model and v1-mini use the LiveKit Model License L6 L8 | BSD-2-Clause P3 | | Runtime model | one process, one isolated async session per call, models on a dedicated thread pool | one OS process per job, "each in its own process for isolation" L7 | documented as one session per process or container P5 | | Needs a media server | no: WebSocket, Twilio and Telnyx built in; WebRTC and SIP are cargo features | yes: a LiveKit server Cloud or self-hosted , the agent joins a room L6 | no for WebSocket and SmallWebRTC; the Daily and LiveKit transports use those vendors' infrastructure P7 | | Telephony | Twilio and Telnyx media streams, SIP trunk listener, DTMF, transfer | LiveKit SIP service: Twilio, Telnyx, Plivo and others, DTMF, cold and warm transfer L12 | Twilio, Telnyx, Plivo, Exotel serializers P7 ; no SIP stack of its own found in the pages read inferred | | Turn detection | Smart Turn v3.2 ONNX, on device with an adaptive policy | own turn-detector models: a text model 396 MB on disk, about 50-160 ms per turn on CPU and the audio model v1-mini its size and cost are not stated L8 | Smart Turn v3 8 MB int8 P8 P10 | | Turkish | first class docs/TURKISH.md https://github.com/bilal07karadeniz/brisvox/blob/main/docs/TURKISH.md | listed by both turn detectors L8 | listed by Smart Turn P10 | | Interruptions | turn epochs; context keeps only the text actually played | adaptive mode separates interruptions from backchannel, resumes after a false one L13 | cancels LLM and TTS, flushes audio, commits only the played text; a minimum-words turn-start strategy and a Krisp backchannel filter P12 | | Tools | read only / side effect kinds, idempotency keys, never speculative; written in Rust, Python or TypeScript | function tools, async tools, handoff, MCP Python , provider-side tools; parallel calls not stated on the page read L15 | parallel calls by default, async tools, per-tool timeouts, cancel on interruption; MCP not checked P13 | | Speech-to-speech | OpenAI Realtime, Gemini Live | many realtime models L16 | several P4 | | Overload handling | admission control and graceful drain built in | default load function 5 s average CPU, threshold 0.7 L11 L17 | none found in the docs; autoscaling guidance P5 | | Hosted cloud | none, self-host only | optional LiveKit Cloud L6 | optional Pipecat Cloud P5 P14 | | Vendor sizing guidance | none, see the measured rows | 4 cores / 8 GB for 10-25 jobs; a vendor test of 30 agents peaked at about 3.8 cores and 2.8 GB L11 | Pipecat Cloud profile of 0.5 vCPU / 1 GB per session P6 | None of this is an independent benchmark: no third-party density comparison of the three was found research notes https://github.com/bilal07karadeniz/brisvox/blob/main/docs/research/frameworks-2026-10-14.md 3-independent-benchmarks-2025-2026 . Prebuilt binary. Every release has brisvox-server archives for Linux x86 64, aarch64 , macOS aarch64 and Windows x86 64 with a SHA256SUMS file, on the Releases page https://github.com/bilal07karadeniz/brisvox/releases . Linux binaries need glibc 2.39 or newer. v=v0.1.4; t=x86 64-unknown-linux-gnu pick the release and your platform curl -fLO https://github.com/bilal07karadeniz/brisvox/releases/download/$v/brisvox-server-$v-$t.tar.gz curl -fLO https://github.com/bilal07karadeniz/brisvox/releases/download/$v/SHA256SUMS sha256sum --ignore-missing -c SHA256SUMS && tar xzf brisvox-server-$v-$t.tar.gz cd brisvox-server-$v-$t python3 scripts/models/fetch models.py the Smart Turn model pinned SHA-256 ./brisvox-server --version Docker. A multi-architecture image linux/amd64 , linux/arm64 with the Smart Turn model inside: docker run --rm ghcr.io/bilal07karadeniz/brisvox-server:latest --version Tags are vX.Y.Z and latest . Running it with an agent file and your keys: Docker and compose https://github.com/bilal07karadeniz/brisvox/blob/main/book/src/quickstart/docker.md . From crates.io. Needs Rust 1.99 or newer, a C compiler and cmake libopus, ONNX Runtime : cargo install brisvox-server --locked --features all-providers,call-control,smart-turn-ort,mcp,webrtc What to build with. The prebuilt binaries and the image are built with all-providers,call-control,smart-turn-ort,mcp,webrtc : every STT/LLM/TTS adapter, the carriers' call control transfer call , send dtmf , end call , Smart Turn on ONNX Runtime, MCP tools and the WebRTC listener. The crate's own default features are deliberately small no provider adapter : an application that only needs some of them names just those, for example --features provider-deepgram,provider-openai,provider-cartesia . Not in the prebuilt set: sip the SIP trunk listener , otlp OpenTelemetry export and recording-encryption ; build from source with them added when you need them. SDKs. pip install brisvox Python 3.11+; installs brisvox-agent, the SDK itself npm i brisvox TypeScript / Node 20+; brisvox/web is the browser client The short names are umbrella packages: brisvox on PyPI depends on brisvox-agent and re-exports it, brisvox on npm depends on @brisvox/agent and @brisvox/web and re-exports them the agent SDK as brisvox , the browser module as brisvox/web . Install the specific packages instead if you want only one: pip install brisvox-agent Python 3.11+ npm install @brisvox/agent TypeScript / Node 20+ npm install @brisvox/web the browser module for a "Talk to us" button As a Rust library. cargo add brisvox --features all-providers is one dependency for a server with your own Rust tools: it re-exports brisvox-server , the tools API brisvox-agent , the provider adapters and the core types, and forwards the server's features. The other crates brisvox-server , brisvox-core , brisvox-agent , brisvox-providers , brisvox-transport , brisvox-engine , brisvox-agent-link , brisvox-inference , brisvox-audio , brisvox-sim are on crates.io too, for those who need one alone. Release notes are in the changelog https://github.com/bilal07karadeniz/brisvox/blob/main/CHANGELOG.md ; security reports go to the security policy https://github.com/bilal07karadeniz/brisvox/blob/main/SECURITY.md . A voice agent that runs entirely on your computer speech recognition, language model and voice, CPU only , talked to in the browser. Needs Docker, 4+ cores, 8 GB of memory; the first start downloads about 6.5 GB. docker compose -f deploy/local/compose.yaml up then open http://localhost:8088/demo?force=ws Details, a larger model for faster machines and the licences: deploy/local/ https://github.com/bilal07karadeniz/brisvox/blob/main/deploy/local/README.md . Needs Rust the toolchain is pinned in rust-toolchain.toml and API keys for the example agent's providers: Deepgram STT , OpenAI LLM and Cartesia TTS . cargo build --release -p brisvox-server --features all-providers,smart-turn-ort,demo-tools python3 scripts/models/fetch models.py the Smart Turn model pinned SHA-256 export DEEPGRAM API KEY=... OPENAI API KEY=... CARTESIA API KEY=... BRISVOX AGENT FILE=examples/agents/support-en.toml target/release/brisvox-server ws on :8080 in another shell: play a recorded utterance at it and measure the answer time cargo run --release -p brisvox-bench -- v2v --url ws://127.0.0.1:8080/ --fixtures en two utterances --runs 1 Your own tools and logic, in Python or TypeScript: python from brisvox agent import Agent agent = Agent "luigi", system prompt="You are Luigi's host.", greeting="Hi, Luigi's here " @agent.tool async def opening hours day: str - str: """Opening hours of the restaurant on a weekday.""" return "12:00 to 22:00" agent.run port=8765 server side: BRISVOX AGENT URL=ws://127.0.0.1:8765 Or with Docker: cp deploy/ws.env.example deploy/ws.env , fill in the keys, then docker compose -f deploy/compose.yaml up --build agent-ws . More in the book: Quickstart https://github.com/bilal07karadeniz/brisvox/blob/main/book/src/quickstart.md ; fully local with no API key: A fully local assistant https://github.com/bilal07karadeniz/brisvox/blob/main/book/src/quickstart/local.md . The default build has no providers and no listeners beyond the websocket; you choose cargo features for what you want to run. The same names go into the Docker image through the BRISVOX FEATURES build argument default all-providers,call-control,smart-turn-ort , which has no webrtc . all-providers can be replaced by the individual provider- features to keep the binary smaller. | Goal | Cargo features --features | Docker --build-arg BRISVOX FEATURES= | Read | |---|---|---|---| | A voice button on a website browser, WebRTC with a WebSocket fallback | all-providers,smart-turn-ort,webrtc | all-providers,smart-turn-ort,webrtc | web assistant https://github.com/bilal07karadeniz/brisvox/blob/main/examples/web-assistant , hosting, incl. one-port platforms https://github.com/bilal07karadeniz/brisvox/blob/main/docs/DEPLOY.md add call-control if the same server also takes phone calls | | A phone number through Twilio or Telnyx transfer, DTMF, hang-up | all-providers,call-control,smart-turn-ort | the default | phone receptionist https://github.com/bilal07karadeniz/brisvox/blob/main/examples/phone-receptionist , Telephony https://github.com/bilal07karadeniz/brisvox/blob/main/docs/TELEPHONY.md | | A SIP trunk | all-providers,call-control,smart-turn-ort,sip | all-providers,call-control,smart-turn-ort,sip | Telephony https://github.com/bilal07karadeniz/brisvox/blob/main/docs/TELEPHONY.md , Deploying https://github.com/bilal07karadeniz/brisvox/blob/main/docs/DEPLOY.md | | Fully local speech sherpa-onnx, Ollama, Kokoro , no API key | provider-sherpa-onnx,provider-openai-compatible,provider-openai-speech,smart-turn-ort,webrtc | the same list | A fully local assistant https://github.com/bilal07karadeniz/brisvox/blob/main/book/src/quickstart/local.md | | Your own tools in Python or TypeScript | the features of the goal above; tools come from an SDK process | the same | SDKs https://github.com/bilal07karadeniz/brisvox/blob/main/sdk/python/README.md , booking agent https://github.com/bilal07karadeniz/brisvox/blob/main/examples/booking-agent | | Your own tools in Rust, in one binary | your crate depends on brisvox-server with the provider features your agent file names and smart-turn-ort , webrtc , call-control as above | build your own image from your crate | Rust tools https://github.com/bilal07karadeniz/brisvox/blob/main/examples/rust-tools , Tools https://github.com/bilal07karadeniz/brisvox/blob/main/docs/TOOLS.md | smart-turn-ort is the end-of-turn model: without it, and the model file from python3 scripts/models/fetch models.py , adaptive turns end at a 3 second fallback deadline. Before you run anything, target/release/brisvox-server check