OpenRouter for Voice

Every speech model, benchmarked language by language, wired into one API.

Router

Which model to call, per language and per objective, decided from published measurements instead of a vendor's English leaderboard.

Benchmark coverage by language

Model

Nova-3

stt-rt-v5

GPT-4o Transcribe

GPT-4o-mini Transcribe

Qwen3-ASR

Chirp 3

Ink-Whisper

Pulse Pro

Whisper-1

Nova-2

Gradium ASR

GPT Transcribe / batch endpoint

Grok STT

Ink-2

Pulse

Realtime STT-1bench

Scribe v2 / historical batch

Scribe v2 Realtime

Solaria-1

Universal-3.5 Pro

Velma 2

Flux

GPT Live Transcribe

Score against cost, per stage

Accuracy (WER)

$0.0010$0.01602.0%11.0%

Universal-3.5 Pro2.0% · $0.0075

Realtime STT-13.3% · $0.0025

GPT-4o-mini Transcribe2.7% · $0.0030

GPT-4o Transcribe2.3% · $0.0060

Velma 24.4% · $0.0010

Cost ($/min)

#Model

Universal-3.5 Proassemblyai:universal-3-5-pro

2.0%$0.0075

GPT-4o Transcribeopenai:gpt-4o-transcribe

2.3%$0.0060

GPT Transcribe / batch endpointopenai:gpt-transcribe

2.5%—

GPT-4o-mini Transcribeopenai:gpt-4o-mini-transcribe

2.7%$0.0030

Qwen3-ASRalibaba:qwen3-asr-flash

2.8%$0.0054

Scribe v2 / historical batchelevenlabs:scribe_v2

2.9%—

Realtime STT-1benchmark only — not routable

3.3%$0.0025

Chirp 3google:chirp_3

3.9%$0.0160

Velma 2modulate:velma-2-stt-streaming-english-v2

4.4%$0.0010

Grok STTxai:stt

4.8%$0.0033

Solaria-1gladia:solaria-1

5.0%$0.0125

Pulsesmallest:pulse

5.1%~$0.0050

stt-rt-v5soniox:stt-rt-v5

7.5%$0.0020

Gradium ASRgradium:default

8.4%$0.0104

Nova-3deepgram:nova-3

9.8%$0.0048

Ink-2cartesia:ink-2

11.0%$0.0090

—

Scribe v2 Realtimeelevenlabs:scribe_v2_realtime

—$0.0065

—

Fluxdeepgram:flux-general-en

—$0.0065

—

GPT Live Transcribeopenai:gpt-live-transcribe

—$0.0170

Gateway

One base URL and one key in front of every provider, speaking the API your framework already calls.

Run and observe your voice workers

Speko speaks the OpenAI API, so the frameworks you already use need a hostname and a model string.

import { defineAgent, voice } from '@livekit/agents';
import * as openai from '@livekit/agents-plugin-openai';

const key = process.env.SPEKO_API_KEY!;
const baseURL = 'https://api.speko.ai/v1';

export default defineAgent({
  entry: async (ctx) => {
    const session = new voice.AgentSession({
      stt: new openai.STT({ apiKey: key, baseURL, model: 'auto' }),
      llm: new openai.LLM({ apiKey: key, baseURL, model: 'auto' }),
      tts: new openai.TTS({ apiKey: key, baseURL, model: 'auto' }),
    });
    await session.start({ agent: new voice.Agent({ ... }) });
  },
});

Point your agent at Speko

$claude mcp add --transport http speko https://mcp.speko.ai/mcp

Read the docs Get API key