Describe it.
We build it.
You own it.
Speko is the voice layer for your product. Describe the agent you want — we benchmark every STT, LLM and TTS provider and route every call to the proven best. One API. No per-provider keys. Live in minutes.
Don’t take our word for it.
Talk to one.
Talk to Speko’s own agent — it answers anything about the platform in real time, retrieved live from our docs. No script, no decision tree. Ask something easy, then try to break it.
From a sentence to a shipped agent.
No provider sprawl, no glue code. Describe the agent you want — Speko assembles and routes the proven-best stack, and you ship.
- 01
Describe it
Tell Speko what your agent should do, in plain English.
- 02
Speko routes it
We continuously benchmark every STT, LLM and TTS provider and assemble the proven-best stack for your use case and language.
- 03
Test it live
Talk to it in the browser or get a real phone call. Tune voice, latency and accuracy in real time.
Try the live demo - 04
Ship & own it
Deploy to a phone number, web widget or API. Your keys, your data, your agent.
Build your agent
We benchmark so you don't have to.
Speko continuously tests every provider on accuracy, latency and cost, then routes each call to the winner. Here's the current English STT field.
English WER · FLEURS · lower is better- 01 ElevenLabs Scribe v2 Realtime 3.4%
- 02 Alibaba qwen3-asr-flash 3.5%
- 03 AssemblyAI Universal-3 Pro 5.1%
- 04 Google Cloud Chirp 2 5.4%
- 05 ElevenLabs Scribe v1 5.4%
- 06 Google Gemini 2.5 Flash (STT) 6.0%
The fastest retrieval
in voice.
A voice agent has ~200 ms to think. Our voice-native retrieval engine answers in sub-millisecond time — so memory never eats your latency budget.
95.8–100% recall vs an exact search, at 0.76 ms across 100K documents.
Speko measured in-process at 100K docs. ChromaDB, Pinecone and Qdrant are their published figures for network-hosted deployments — includes network transport, not like-for-like.
One API. Every surface.
However your users reach you, Speko answers — with one integration.
// illustrative
import { Speko } from "@spekoai/sdk";
const speko = new Speko({ apiKey: process.env.SPEKO_KEY });
const agent = await speko.agents.create({
intent: "Book appointments for a dental clinic",
channels: ["phone", "web"],
});
console.log(agent.phoneNumber); // +1 …Good questions.
What is Speko?
A voice-AI gateway. One API gives you speech-to-text, an LLM and text-to-speech, provider-agnostic. Speko benchmarks every provider and routes each call to the proven-best stack.
Do I need my own provider API keys?
No. One Speko key covers it — we manage provider credentials, routing and failover. Bring-your-own keys are optional if you prefer.
How does routing choose a provider?
Continuous benchmarks on accuracy (WER), latency and cost, per language and use case. Each call gets the best stack, with automatic failover if a provider degrades.
What latency can I expect?
Around 340 ms median for a conversational turn. You can optimize any agent for latency, accuracy or cost.
Who owns the data and the agent?
You do. Your audio and transcripts aren't used to train models, and you can export your configuration at any time.
How fast can I launch?
Under five minutes from a plain-English description. Talk to your agent in the browser before you ship it to a phone number or the web.
Your first agent is waiting.
Describe it in a sentence. Hear it in a minute. Ship it today.