--- title: "Retell AI alternatives" description: "Compare Retell AI with Speko Agents, Vapi, Synthflow, Pipecat and LiveKit Agents. See telephony, pricing and who runs the agent, with sources." canonical: "https://speko.ai/retell-alternatives" 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. # Retell AI alternatives Comparison Retell AI and five alternatives, compared on telephony, pricing and who runs the agent. Two of them, Speko Agents and Speko Router, are ours, and we describe them ourselves. Short answer Retell AI lists $0.07 to 0.31 per minute for AI voice agents, priced as components. The hosted alternatives are Speko Agents ($0.09 per minute, all-in), Vapi and Synthflow. The build-it-yourself alternatives are Pipecat and LiveKit Agents. **By** Speko engineering **Published** November 10, 2026 **Updated** November 11, 2026 ## Which alternative for which team? - ### Which Retell AI alternative includes the models in one per-minute price? - Speko Agents ours **Why** Speko Agents lists $0.09 per minute with speech-to-text, LLM and text-to-speech included, plus carriage on Speko numbers. Retell AI lists $0.07 to 0.31 per minute for AI voice agents, assembled from voice infrastructure, text-to-speech, LLM and telephony components. - ### Which Retell AI alternative is best for calls in several languages? - Speko Agents ours **Why** Speko Agents holds up to four languages per agent and switches when the caller does. Each language uses its own speech-to-text, LLM and text-to-speech, chosen from Speko's independent benchmark of speech models by language. - ### Which Retell AI alternative is a developer platform? - Vapi **Why** Vapi is a hosted developer platform for voice agents, listing $0.05 per minute Vapi hosting, pre-paid with models passed through at cost. - ### Which Retell AI alternative fits a team that buys on an annual contract? - Synthflow **Why** Synthflow sells annual enterprise agreements scoped to call volume and phone system. Its pricing page lists no rate by the minute. - ### What if my team wants to own the runtime instead? - Pipecat - LiveKit Agents - Speko Router ours **Why** Move to Pipecat or LiveKit Agents for the conversation loop, and add Speko Router inside it for benchmark-ranked speech and language models. [Get started free](https://platform.speko.ai/sign-in) [Book a demo](https://speko.ai/book) ## How do the Retell AI alternatives compare? | Option | Who runs the agent | Published price | Phone calls | How you buy | | --- | --- | --- | --- | --- | | Retell AI the baseline | Retell hosts it | $0.07 to $0.31/min Range set by the components you choose | Retell carrier or custom SIP, priced separately | Self-serve, no platform fee | | Speko Agents (hosted) our product | Speko hosts it | $0.09/min Speech-to-text, LLM and text-to-speech included | Included: Speko numbers or your SIP trunk | Self-serve, no contract | | Vapi | Vapi hosts it | $0.05/min Hosting only; models billed at cost on top | Connected and billed separately | Self-serve, pay as you go | | Synthflow | Synthflow hosts it | No published rate Annual enterprise agreement; no rate by the minute | Synthflow telephony, Twilio or SIP | Annual enterprise agreement | | Pipecat | Your team runs it, or Pipecat Cloud | Open source; you pay your own providers | The transport your app picks | Open source | | LiveKit Agents | Your team runs it, or LiveKit Cloud | $0.01/min Agent hosting only; models billed on top | LiveKit SIP and Cloud numbers | Open source; Cloud plans from $0 | | Speko Router + Gateway our product, model layer only | Your runtime; Speko routes the models | $0.09/min on Speko infra, or +5% on your provider's rate | Stays with your runtime | Self-serve, no contract | **See the full statements, with sources** | Option | Category | Telephony | Pricing model | Sources | | --- | --- | --- | --- | --- | | Retell AI the baseline | Hosted phone-agent platform. | Published options include Retell carrier service and custom SIP, priced as separate components. | Component pricing: voice infrastructure plus selected TTS, LLM, telephony and optional features. | [Retell AI pricing](https://www.retellai.com/pricing) [Retell AI documentation](https://docs.retellai.com/) | | Speko Agents (hosted) our product | Hosted voice agent platform with phone numbers, calls and SMS. | 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. | $0.09 per minute all-in for STT, LLM and TTS, billed from answer to hang-up. Calls on a Speko number add carriage; calls over your own SIP trunk add nothing. | [Build a phone agent (Speko docs)](https://docs.speko.ai/guides/phone-agents) [SMS on Speko (Speko docs)](https://docs.speko.ai/sms) [Build an agent in the dashboard (Speko docs)](https://docs.speko.ai/quickstart/dashboard) [Speko pricing](https://speko.ai/pricing) | | Vapi | Hosted developer platform for voice agents. | Telephony is connected and billed separately from Vapi hosting and orchestration. | Usage-based hosting and orchestration, plus model and telephony charges; BYOK providers can bill directly. | [Vapi pricing](https://vapi.ai/pricing) [Vapi pricing FAQ](https://docs.vapi.ai/faq) [Vapi documentation](https://docs.vapi.ai/) [Vapi provider keys](https://docs.vapi.ai/customization/provider-keys) [Vapi transcriber fallback](https://docs.vapi.ai/customization/transcriber-fallback-plan) | | Synthflow | Hosted voice agent platform sold on annual enterprise agreements. | Synthflow Native Telephony, SIP trunking or approved enterprise telephony. Numbers can be bought through Synthflow, kept in Twilio, or imported over SIP on an Enterprise account. | An annual enterprise agreement scoped to call volume and phone system. Synthflow's pricing page says it has no free plan or trial and no rate by the minute. Its phone-number docs list purchased numbers at $1.50 a month. | [Synthflow pricing](https://synthflow.ai/pricing) [Synthflow documentation](https://docs.synthflow.ai/getting-started) [Synthflow phone numbers](https://docs.synthflow.ai/phone-numbers) | | Pipecat | Open-source framework with an optional managed cloud. | A self-hosted application selects its transport or telephony integration. Pipecat Cloud offers managed deployment around Pipecat workloads. | The framework is open source. Self-hosted model, transport and hosting costs are separate; Pipecat Cloud is a separately priced managed service. | [Pipecat documentation](https://docs.pipecat.ai/) [Pipecat Cloud documentation](https://docs.pipecat.ai/pipecat-cloud/introduction) [Pipecat repository](https://github.com/pipecat-ai/pipecat) | | LiveKit Agents | Open-source agent framework with an optional managed cloud. | 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. | 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. | [LiveKit Agents documentation](https://docs.livekit.io/agents/) [LiveKit pricing](https://livekit.com/pricing) | | Speko Router + Gateway our product, model layer only | Voice model router: hosted Router plus an open customer-side Gateway for STT, LLM and TTS. | Not included. Your runtime handles phone calls and WebRTC. | $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. | [Speko infrastructure guide](https://speko.ai/voice-agent-infrastructure) [Speko pricing](https://speko.ai/pricing) | ## What do Retell AI and the alternatives cost? - 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 Retell AI 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 Retell AI agent Ask it to convert your Retell AI 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) ## The alternatives, one by one **When to choose each alternative** ### Speko Agents (hosted) Our product 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. The whole agent: prompt, voice, tools, knowledge and the phone number live in the Speko console and API. Speko runs the conversation loop. [Speko vs Retell AI](https://speko.ai/speko-vs-retell) [Voice agent testing](https://speko.ai/voice-agent-testing) [Speko pricing](https://speko.ai/pricing) ### Vapi Choose Vapi when your developers want a hosted agent and want to pick each provider themselves. Vapi hosts the agent. You configure its prompts, tools and providers in the platform. [Speko vs Vapi](https://speko.ai/speko-vs-vapi) ### Synthflow Choose Synthflow when a phone agent bought on an annual enterprise agreement, with launch support and contact-center telephony integrations, fits how the team buys. Voice and chat agents built in the Synthflow dashboard or API, each configured with either a Prompt Builder or a Flow Designer. [Speko vs Synthflow](https://speko.ai/speko-vs-synthflow) ### Pipecat Choose Pipecat for code-level control of the realtime conversation loop, and Pipecat Cloud to have it hosted. Speko Router + Gateway can supply the models inside that loop. Pipecat is a code framework for realtime pipelines; Pipecat Cloud is a separate managed deployment service. [Speko vs Pipecat](https://speko.ai/speko-vs-pipecat) [Pipecat with Speko](https://speko.ai/docs/pipecat) ### LiveKit Agents 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. 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. [Speko vs LiveKit Agents](https://speko.ai/speko-vs-livekit) [LiveKit with Speko](https://speko.ai/docs/livekit) ### Speko Router + Gateway Our product Choose it when your application already runs the conversation loop and you want one API for its speech and language models. One API for STT, LLM and TTS model calls. It does not run the conversation loop. It replaces the model clients in your code. Your runtime keeps the phone carrier, the transport and the conversation. [Speko Gateway for LiveKit](https://speko.ai/docs/livekit) [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 - Vendor facts are from each vendor's own pages, linked in the tables, checked November 10, 2026. - Prices are from each vendor's own pricing page, checked November 11, 2026. - Speko Agents facts are from the Speko docs and pricing page, checked November 11, 2026. - Speko measures models and does not rank platforms. 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) - [Vapi alternatives](https://speko.ai/vapi-alternatives) - [Synthflow alternatives](https://speko.ai/synthflow-alternatives) - [Speko vs Retell AI](https://speko.ai/speko-vs-retell) - [Voice agent testing](https://speko.ai/voice-agent-testing) - [Multilingual voice agents](https://speko.ai/multilingual-voice-agents) - [Voice agents by business](https://speko.ai/solutions) - [Speko pricing](https://speko.ai/pricing)