--- title: "Speko vs LiveKit Agents" description: "Build the voice agent yourself on LiveKit Agents, or let Speko Agents host it. Compare scope, telephony, routing, operations and pricing, with sources, and see how the two work together." canonical: "https://speko.ai/speko-vs-livekit" last-updated: "2026-11-10" --- > ## 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. # Speko vs LiveKit Agents Comparison Speko Agents runs the agent for you. With LiveKit Agents, your team runs it. The two also work together. Short answer Choose LiveKit Agents to own the conversation loop in code. Choose Speko Agents to let Speko host the loop, phone numbers, testing and monitoring at $0.09 per minute. If you already run LiveKit, keep it and add Speko Router through @spekoai/adapter-livekit. **By** Speko engineering **Published** November 10, 2026 **Updated** November 11, 2026 ## Which should you pick: Speko or LiveKit Agents? ### Pick Speko Agents whenours - You want phone numbers, inbound and outbound calls, SMS and transfers in one console. - You want one price per minute, with speech-to-text, LLM and text-to-speech included. - You want to test an agent with simulated callers and score every real call. ### Pick LiveKit Agents when - The team wants to build the realtime conversation loop in code, in Python or Node.js. - Agents should run on the team's own infrastructure, or on LiveKit Cloud's managed agent deployments. - Phone calls should run through LiveKit's SIP integration alongside web and mobile clients. [Get started free](https://platform.speko.ai/sign-in) [Book a demo](https://speko.ai/book) ## How do Speko and LiveKit Agents compare? | | Speko Agents ours | LiveKit Agents | | --- | --- | --- | | Who runs the agent | Speko hosts it | Your team runs it, or LiveKit Cloud | | Published price | $0.09/min Speech-to-text, LLM and text-to-speech included | $0.01/min Agent hosting only; models billed on top | | Phone calls | Included: Speko numbers or your SIP trunk | LiveKit SIP and Cloud numbers | | How you buy | Self-serve, no contract | Open source; Cloud plans from $0 | **See the full comparison, with sources** | Dimension | Speko Agents (hosted) Hosted phone agents | LiveKit Agents | Speko Router + Gateway Model layer, your runtime | | --- | --- | --- | --- | | Category | Hosted voice agent platform with phone numbers, calls and SMS. | Open-source agent framework with an optional managed cloud. | Voice model router. | | Scope | The whole agent: prompt, voice, tools, knowledge and the phone number live in the Speko console and API. Speko runs the conversation loop. | LiveKit Agents is an open-source framework that adds Python or Node.js programs to LiveKit rooms as realtime participants; LiveKit Cloud hosts agent deployments. | One API for STT, LLM and TTS model calls. It does not run the conversation loop. | | Telephony | Included. Inbound and outbound phone calls on a Speko number or on a number you already own (SIP trunk import); SMS on Speko numbers; blind and warm transfers to a human. | An agent places and receives calls through LiveKit's SIP integration. LiveKit Cloud rents US local and toll-free numbers and also carries calls over third-party SIP trunks. | Not included. Your runtime handles phone calls and WebRTC. | | Model routing | Measured selection and pre-response failover across STT, LLM and TTS. An agent can also pin providers, or run on a speech-to-speech model: Grok Voice 3.0 at the same per-minute rate, or GPT-Live, which adds its reasoning model's tokens at the provider's published rate plus 5%. | Developers wire STT, LLM and TTS in code through provider plugins or LiveKit Inference, or point those services at an external router. | Your application can pin a model, or let Speko pick from measured routes. | | Runtime ownership | Speko operates the agent runtime and the phone legs, records the call, persists transcripts and events, and finalizes a call report after hangup. The customer configures the agent. | The application team owns its agent code and runs it on its own infrastructure, or deploys it to LiveKit Cloud's managed agent deployments. | Speko runs the routing API; you keep LiveKit, Pipecat or your own runtime. | | Observability and failover | Lifecycle events, a call report and a recording per call; signed workspace webhooks; call lists of up to 1,000 rows with a call window. | Self-hosted teams run their own operations; LiveKit Cloud adds built-in observability with transcripts and traces. | Response headers give the route, the reason, the failover count and the first-byte time. Failover happens before the response starts, not mid-stream. | | Benchmark transparency | An agent's default stack is computed from the same benchmark dataset that feeds the public boards at speko.ai/benchmarks; the picks are written into the agent at create time. | No sourced statement | Public voice benchmark boards at speko.ai/benchmarks; automatic selection ranks over the published snapshot. | | Pricing model | $0.09 per minute all-in for STT, LLM and TTS, billed from answer to hang-up; unanswered calls cost nothing. Calls on a Speko number add the carrier's charge plus 20%, at least $0.015 per minute outbound and $0.01 per minute inbound; calls over your own SIP trunk add nothing. A Speko number is $1 setup and $2 a month. $10 signup credit. | The framework is open source under Apache 2.0. LiveKit Cloud plans include monthly agent session minutes, then $0.01 per minute on Ship and Scale; LiveKit Inference and telephony are metered separately. | $0.09 per minute on Speko infrastructure for STT, LLM and TTS; phone calls on Speko numbers add the carrier's charge for the call, including its taxes and fees, plus 20%. Current terms are kept on the pricing page. | LiveKit Agents sources: [LiveKit Agents documentation](https://docs.livekit.io/agents/) [LiveKit pricing](https://livekit.com/pricing) ## What does LiveKit Agents cost compared with Speko? - Speko ours Speech-to-text, LLM and text-to-speech included $900 $0.09/min - Vapi Hosting only; models billed at cost on top $500 $0.05/min - Retell AI Range set by the components you choose $700 to $3,100 $0.07 to $0.31/min - Synthflow Annual enterprise agreement; no rate by the minute No published rate - LiveKit Cloud Agent hosting only; models billed on top $100 $0.01/min - Twilio ConversationRelay Speech relay only; voice minutes and your LLM on top $700 $0.07/min Monthly figures use the published per-minute rate only. They leave out plan fees, phone numbers, carriage and any models a vendor bills on top. **See every price term, with sources** | Platform | Per minute | Included | Telephony | Monthly fee | Source | | --- | --- | --- | --- | --- | --- | | Speko our product | $0.09 per minute, all-in | Speech-to-text, LLM and text-to-speech on Speko infrastructure. Billed per second from answer to hang-up; unanswered calls cost nothing. | Calls on Speko numbers add the carrier's charge for the call, including its taxes and fees, plus 20%, at least $0.01 per minute inbound and $0.015 per minute outbound. Calls over your own SIP trunk add nothing. | None. A Speko phone number is $1 setup and $2 a month for most numbers. | [speko.ai/pricing](https://speko.ai/pricing) | | Vapi | $0.05 per minute Vapi hosting, pre-paid | Vapi hosting. Speech-to-text, LLM and text-to-speech are passed through at the provider's cost on top. | Transport is charged by the carrier, not Vapi; Vapi's own SIP transport is listed as free. | None on the usage-only plan (1 included number, 4 concurrent calls). Core $29 a month; Pro $999 a month minimum; HIPAA $2,000 a month. | [vapi.ai/pricing](https://vapi.ai/pricing) | | Retell AI | $0.07 to 0.31 per minute for AI voice agents | Retell voice infrastructure at $0.055 per minute plus the selected text-to-speech and LLM components, each priced per minute. | Retell-provided numbers $0.015 per minute in the US; own SIP trunk or custom telephony at no charge from Retell. | None. A Retell phone number is $2 a month; 20 concurrent calls included, $8 per extra concurrent call a month. | [retellai.com/pricing](https://www.retellai.com/pricing) | | Synthflow | No rate by the minute, per Synthflow's pricing page; annual enterprise agreement | Scoped per contract. | Native telephony or SIP trunking, scoped per contract. | Quote only. Synthflow's pricing page says it has no free plan or trial. | [synthflow.ai/pricing](https://synthflow.ai/pricing) | | LiveKit Cloud | $0.01 per agent session minute after the included minutes on Ship and Scale | Agent hosting on LiveKit Cloud. Models are separate: each plan includes LiveKit Inference credits, and Ship and Scale then bill at model prices. | US local numbers: 1 free, then $1.00 a month on Ship and Scale. After the included minutes, US local inbound is $0.01 per minute and third-party SIP is $0.004 per minute on Ship, $0.003 on Scale. | Build $0 (1,000 agent session minutes); Ship from $50 (5,000); Scale from $500 (50,000); Enterprise custom. | [livekit.com/pricing](https://livekit.com/pricing) | | Twilio ConversationRelay | $0.07 per minute for ConversationRelay | The speech relay between a Twilio call and your own server. Twilio does not say on the pricing page whether speech is included in the rate; your LLM is billed by its own provider. | Twilio Voice, billed separately: US local calls $0.0085 per minute inbound and $0.0140 per minute outbound. | None. A US local number is $1.15 a month. | [twilio.com/voice/pricing/us](https://www.twilio.com/en-us/voice/pricing/us) | ## How do I switch from LiveKit Agents to Speko? 1. ### 1Connect an agent to Speko Add Speko's MCP server to Claude Code, Cursor or Codex. [Set up Claude Code](https://speko.ai/integrations/claude-code) [Set up Cursor](https://speko.ai/integrations/cursor) [Set up Codex](https://speko.ai/integrations/codex) 2. ### 2Convert your LiveKit Agents agent Ask it to convert your LiveKit Agents config. The MCP server reads it and drafts a Speko agent for you to review. [How the conversion works](https://docs.speko.ai/quickstart/mcp) 3. ### 3Bring your number Import your number over a SIP trunk, or buy a Speko number. [Phone number setup](https://docs.speko.ai/guides/phone-agents) 4. ### 4Test, then go live Run simulated callers against the draft. Deploy when the checks pass. [How testing works](https://speko.ai/voice-agent-testing) ## Questions **What is the difference between Speko and LiveKit Agents?** Choose Speko Agents when you want a hosted phone agent with numbers, inbound and outbound calls, SMS and transfers in one console, priced per minute. Choose LiveKit Agents for code-level control of the realtime conversation loop, and LiveKit Cloud to have it hosted. Speko Router + Gateway can supply the models inside that loop. **How is LiveKit Agents priced compared with Speko?** Speko Agents: $0.09 per minute all-in for STT, LLM and TTS, billed from answer to hang-up; unanswered calls cost nothing. Calls on a Speko number add the carrier's charge plus 20%, at least $0.015 per minute outbound and $0.01 per minute inbound; calls over your own SIP trunk add nothing. A Speko number is $1 setup and $2 a month. $10 signup credit. LiveKit Agents: The framework is open source under Apache 2.0. LiveKit Cloud plans include monthly agent session minutes, then $0.01 per minute on Ship and Scale; LiveKit Inference and telephony are metered separately. **Does LiveKit Agents include phone numbers and telephony?** LiveKit Agents: An agent places and receives calls through LiveKit's SIP integration. LiveKit Cloud rents US local and toll-free numbers and also carries calls over third-party SIP trunks. Speko Agents: Included. Inbound and outbound phone calls on a Speko number or on a number you already own (SIP trunk import); SMS on Speko numbers; blind and warm transfers to a human. **Who runs the agent: LiveKit Agents or my team?** LiveKit Agents: The application team owns its agent code and runs it on its own infrastructure, or deploys it to LiveKit Cloud's managed agent deployments. Speko Agents: Speko operates the agent runtime and the phone legs, records the call, persists transcripts and events, and finalizes a call report after hangup. The customer configures the agent. Speko Router + Gateway: Speko runs the routing API; you keep LiveKit, Pipecat or your own runtime. [Get started free](https://platform.speko.ai/sign-in) [Book a demo](https://speko.ai/book) You get $10 in credit when you sign up. Calls then cost $0.09 per minute. ## Notes - LiveKit Agents facts are from its own pages, linked above, checked November 10, 2026. - Prices are from each vendor's own pricing page, checked November 11, 2026. - Speko Agents facts are from [Build a phone agent (Speko docs)](https://docs.speko.ai/guides/phone-agents) and the pricing page, checked November 11, 2026. Speko Router + Gateway facts are from the Speko infrastructure guide and pricing page. - An empty cell means that this page has no sourced statement for that cell. - The benchmark snapshot behind Speko routing is at [speko.ai/benchmarks/data.json](https://speko.ai/benchmarks/data.json). Related - [Voice agent platforms, runtimes and model routers](https://speko.ai/voice-agent-platforms) - [Speko vs Vapi](https://speko.ai/speko-vs-vapi) - [Speko vs Retell AI](https://speko.ai/speko-vs-retell) - [Speko vs Synthflow](https://speko.ai/speko-vs-synthflow) - [Speko vs Pipecat](https://speko.ai/speko-vs-pipecat) - [Speko vs Twilio ConversationRelay](https://speko.ai/speko-vs-twilio) - [Vapi alternatives](https://speko.ai/vapi-alternatives) - [Retell AI alternatives](https://speko.ai/retell-alternatives) - [Synthflow alternatives](https://speko.ai/synthflow-alternatives) - [Voice agent testing](https://speko.ai/voice-agent-testing) - [Voice agent monitoring](https://speko.ai/voice-agent-monitoring) - [Current model catalog](https://speko.ai/models) - [Voice agents by business](https://speko.ai/solutions) - [Speko pricing](https://speko.ai/pricing)