---
title: "The Router for Voice AI"
description: "Hosted Router for managed STT, LLM and TTS routing, plus an open customer-side Gateway for provider-direct voice workloads."
canonical: "https://speko.ai/"
last-updated: "2026-08-24"
---
> ## Speko page index
> The complete index of every page on this site is at: https://speko.ai/llms.txt
> Read it before exploring further. It lists the exact Markdown URL for every canonical HTML page.
# The Router for Voice AI
[Backed by Y Combinator](https://www.ycombinator.com/companies/speko)
Every speech model, benchmarked language by language, wired into one API.
[Get API key](https://platform.speko.ai/sign-in)
## Router
A hosted, provider-neutral STT, LLM and TTS data plane at router.speko.dev, with typed contracts and managed routing.
### Benchmark coverage by language
Model EN (English) ES (Spanish) DE (German) FR (French) AR (Arabic) FIL (Filipino) NB (Norwegian) HI (Hindi) TA (Tamil) TE (Telugu) KO (Korean) ZH (Chinese (Mandarin)) JA (Japanese) TH (Thai)
deepgram:nova-3
openai:gpt-4o-transcribe
soniox:stt-rt-v5
cartesia:ink-whisper
Alibaba:Qwen3-ASR bench
google:chirp_3
OpenAI:GPT-4o-mini Transcribe bench
assemblyai:universal-3-5-pro
openai:gpt-transcribe
Smallest AI:Pulse Pro bench
Deepgram:Nova-2 bench
xai:grok-stt
Alibaba:Qwen-ASR bench
ElevenLabs:Scribe v2 bench
Gladia:Solaria-1 bench
gradium:default
modulate:velma-2-stt-streaming
ElevenLabs:Scribe v1 bench
OpenAI:GPT-4o mini Transcribe bench
alibaba:qwen3-asr-flash-realtime
elevenlabs:scribe_v2_realtime
AssemblyAI:Universal (batch tier) bench
azure:MAI-Transcribe-2
cartesia:ink-2
fish:transcribe-1
fish:transcribe-1-pro
Hamsa:S3 bench
modulate:velma-2-stt-streaming-english-v2
nari:qwen3-asr
nari:qwen3-asr-fast
smallest:pulse
speechmatics:enhanced
speechmatics:standard
Hover a cell for its number.
worse better
20 of 47
are only measured in English
Their rank in any other language is unknown — including the model that sits at the top of the English table.
5
different models win across 14 languages
No single model is best everywhere, so the right pick changes with the language your users speak.
### Score against cost, per stage
Accuracy (WER · conversational)
25ms 4.57s 12.0% 35.2%
Qwen3-ASR Fast 12.0% · 33ms
Qwen3-ASR 12.0% · 25ms
Finalize (ms, p50)
Model
Qwen3-ASR Fast nari:qwen3-asr-fast
12.0% 33ms
Qwen3-ASR nari:qwen3-asr
12.0% 25ms
Qwen3-ASR Realtime alibaba:qwen3-asr-flash-realtime
12.2% 889ms
Scribe v2 Realtime elevenlabs:scribe_v2_realtime
12.5% 1.75s
Gemini 3.5 Transcribe Live gemini:gemini-3.5-transcribe-live
13.1% 1.28s
GPT Live Transcribe openai:gpt-live-transcribe
13.5% 620ms
Grok Voice Transcribe 1.0 xai:grok-stt
13.7% 1.13s
Universal-3.6 Pro assemblyai:universal-3-6-pro
13.7% 505ms
Muse Voice Transcribe meta:muse-voice-transcribe-1.0
14.2% —
Velma 2 modulate:velma-2-stt-streaming-english-v2
14.4% 1.21s
Pulse smallest:pulse
14.5% 839ms
Universal-3.5 Pro assemblyai:universal-3-5-pro
14.5% 408ms
Enhanced speechmatics:enhanced
15.1% 4.49s
stt-rt-v5 soniox:stt-rt-v5
16.6% 340ms
Ink-2 cartesia:ink-2
16.7% 587ms
GPT Realtime Whisper openai:gpt-realtime-whisper
16.8% 1.14s
GPT Transcribe openai:gpt-transcribe
16.8% 817ms
Nova-3 deepgram:nova-3
17.0% 189ms
Standard speechmatics:standard
18.1% 4.57s
Chirp 3 google:chirp_3
18.4% —
Flux deepgram:flux-general-en
19.7% 712ms
flux-general-multi deepgram:flux-general-multi
21.4% 854ms
Gradium ASR gradium:default
24.2% 1.13s
Universal-Streaming English assemblyai:universal-streaming-english
26.2% 452ms
GPT-4o Transcribe openai:gpt-4o-transcribe
32.9% 848ms
Universal-Streaming Multilingual assemblyai:universal-streaming-multilingual
35.2% 495ms
transcribe-1-pro fish:transcribe-1-pro
— —
transcribe-1 fish:transcribe-1
— —
MAI-Transcribe-2 azure:MAI-Transcribe-2
— —
ink-whisper cartesia:ink-whisper
— —
gemini-3.5-transcribe gemini:gemini-3.5-transcribe
— —
velma-2-stt-streaming modulate:velma-2-stt-streaming
— —
default palabra:default
— —
## Gateway
The open customer-side runtime for LiveKit and Pipecat: provider-direct streaming, local BYOK credentials and optional Speko-managed routes.
### Run and observe your voice workers
Use the native Gateway integrations in your framework, or call the hosted Router through its public OpenAPI and AsyncAPI contracts.
```python
from livekit.agents import AgentSession
from speko_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 Speko
```bash
$ claude mcp add --transport http speko https://mcp.speko.ai/mcp
```
[Read the docs](https://docs.speko.ai) [Get API key](https://platform.speko.ai/sign-in)