









Speko is a voice AI routing and infrastructure platform that provides a unified API for speech-to-text, language models, and text-to-speech. It benchmarks speech and language models across multiple languages, routes each session to suitable-performing models, and supports provider-direct or managed voice workflows through integrations with LiveKit, Pipecat, OpenAPI, AsyncAPI, and MCP.
Create a Speko account and obtain an API key. Choose between routing requests through Speko's managed Router or using Speko infrastructure at a bundled per-minute rate. Integrate with LiveKit, Pipecat, MCP, OpenAPI, or AsyncAPI, then configure speech-to-text, LLM, and text-to-speech services using provider credentials or Speko-managed routes. Set routing objectives such as balanced performance and monitor voice workers through the supported integrations.

Router
+5% on the provider's published rate
Provider-published rates for speech-to-text, LLM, and text-to-speech, plus measured model selection and pre-response failover. Public preview access, email support, no SLA during preview, and no commitment.
Speko Infrastructure
$0.09 per minute
Speech-to-text, LLM, and text-to-speech included in one per-minute rate, with measured model selection and pre-response failover. Public preview access, email support, no SLA during preview, and no commitment.
Enterprise
Custom pricing
Speech-to-text, LLM, and text-to-speech included, with additional deployment reviews, dedicated support, contractual SLA, and a committed monthly minimum.
Signup Credit
$100 credit
Signup credit applies to every account before paid usage.


64.62%

Social Listening