Backed by Y Combinator · S26

Ship voice agents
in minutes

One API for the whole voice stack, routed to the best provider on every call. No keys, no setup.

or talk to it live

Routed across every major provider

  • OpenAI
  • ElevenLabs
  • Deepgram
  • Anthropic
  • Google
  • Cartesia
  • AssemblyAI
  • Whisper
  • Alibaba
  • xAI
10+ providers benchmarked
47+ provider combos
1 API key, every provider
<5min idea to live
See the live benchmarks
Live demo

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.

Try asking
Tap to talk. It answers from our docs, live
How it works

From a sentence to a shipped agent.

No provider sprawl, no glue code. Describe the agent you want, and Speko assembles and routes the proven-best stack, then you ship.

  1. 01

    Describe it

    Tell Speko what your agent should do, in plain English.

  2. 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.

  3. 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
  4. 04

    Ship & own it

    Deploy to a phone number, web widget or API. Your keys, your data, your agent.

    Build your agent
The leaderboard

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
  1. 01 ElevenLabs Scribe v2 Realtime 3.4%
  2. 02 Alibaba qwen3-asr-flash 3.5%
  3. 03 AssemblyAI Universal-3 Pro 5.1%
  4. 04 Google Cloud Chirp 2 5.4%
  5. 05 ElevenLabs Scribe v1 5.4%
  6. 06 Google Gemini 2.5 Flash (STT) 6.0%
Also benchmarked
STT TTS Speech-to-Speech Voice-LLMs
View the full leaderboard
Retrieval

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.

Retrieval p50 100K docs · lower is better
Speko 0.76ms
ChromaDB 352ms
Pinecone 433ms
Qdrant 598ms

Speko measured in-process at 100K docs. ChromaDB, Pinecone and Qdrant are their published figures for network-hosted deployments, which include network transport, so it isn't like-for-like.

Ship it anywhere

One API. Every surface.

However your users reach you, Speko answers with one integration.

Phone number Inbound and outbound calls over SIP. Bring a number or get one.
Web & mobile widget Drop-in voice widget, or wire the SDK into your app.
API & webhooks Full programmatic control with @spekoai/sdk and event webhooks.
create-agent.ts 
// 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 …
Get your API key Read the docs
1 API to learn
0 provider keys to manage
∞ scale
Questions

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 and routing, and 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 proven-best stack for that language and use case.

What latency can I expect?

It depends on the stack you run — STT, LLM and TTS each add latency. Rather than quote one number, we publish measured per-provider latency in the open benchmark, and 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.

Start now

Your first agent is waiting.

Describe it in a sentence. Hear it in a minute. Ship it today.

Build your agent Talk to the founders
YC S26 SOC 2 in progress founders@speko.ai

Speko

One API for the whole voice stack — STT, LLM, and TTS — benchmarked in real time and routed to the best provider on every call, with automatic failover, in 10+ languages.

Connect your agent

MCP-first. Speko runs a hosted, OAuth-protected MCP server — no local install required. Point any MCP client at it and your agent gets authenticated, operational access to the Speko voice gateway.

# Guided setup for any supported client
npx @spekoai/mcp@latest init

# Hosted endpoint
https://mcp.speko.ai/mcp
# Claude Code — add with OAuth, then run /mcp to sign in
claude mcp add --transport http speko https://mcp.speko.ai/mcp

# Or with an API key instead of OAuth
claude mcp add --transport http speko https://mcp.speko.ai/mcp \
  --header "Authorization: Bearer sk_live_xxx"
// Cursor — Settings > MCP > Add new global MCP server
{
  "mcpServers": {
    "speko": {
      "url": "https://mcp.speko.ai/mcp"
    }
  }
}

Authenticate with OAuth when your client supports it, or send a Speko API key as `Authorization: Bearer sk_live_xxx`. Once connected, the server exposes operational tools for: organizations (usage + credit balance), agents (create / update / deploy / roll back), sessions, calls (transcripts + recordings), phone numbers, knowledge bases, evals, deployment, a docs.search self-serve tool, and migration helpers to convert external voice-agent configs.

SDKs

Full programmatic control of the gateway from your language of choice.

Read

Machine-readable indexes first, then concepts and the live benchmarks that drive routing.

What it is

Speko is an OpenRouter-style gateway for voice AI: one API for every voice provider. It continuously benchmarks STT, LLM, and TTS providers on accuracy, latency, and cost, then routes each call to the proven-best stack for your language and target — with automatic failover across the full voice stack (STT, TTS, and speech-to-speech) in 10+ languages. No per-provider keys, no glue code. Around 340 ms median for a conversational turn. Describe an agent in plain English and talk to it in the browser before you ship it to a phone number, web widget, or API. Your keys, your data, your agent.

Build