The router
for voice AI
Every speech model, benchmarked language by language, wired into one API.
A hosted, provider-neutral data plane
A hosted, provider-neutral STT, LLM and TTS data plane at router.patchboard.online, with typed contracts and managed routing.
Their rank in any other language is unknown — including the model that sits at the top of the English table.
No single model is best everywhere, so the right pick changes with the language your users speak.
Studies per language across the speech-to-text and text-to-speech boards. Full per-language rankings live on the models page.
Every model, ranked against what it actually costs
Speech-to-text, LLM, text-to-speech and speech-to-speech — accuracy plotted against dollars per minute, so the trade-off is visible instead of assumed.
The open customer-side runtime
The open customer-side runtime for LiveKit and Pipecat: provider-direct streaming, local BYOK credentials and optional Patchboard-managed routes.
Provider keys stay in your process, never Patchboard's.
Call providers directly, or route through Patchboard.
from livekit.agents import AgentSession
from patchboard_gateway.livekit import LLM, STT, TTS
session = AgentSession(
stt=STT(credential_source="auto"),
llm=LLM(model="auto", objective="balanced"),
tts=TTS(credential_source="auto"),
)Point your agent at Patchboard
Run and observe your voice workers with the hosted Router's public OpenAPI and AsyncAPI contracts, or via MCP.
$ claude mcp add --transport http patchboard https://mcp.patchboard.online/mcp