Top 6 of 21 alternatives
Alternatives to Retell AI
Find a better fit. See what each alternative to Retell AI does better, where it falls short, and what it costs.
On this page
- 01
Vapi
Developer platform for building, testing and deploying voice AI agents that make and receive phone calls.
From $0.05/minuteWhy it's on this listThe closest developer-first rival — also model-agnostic and billed per minute, with a cheaper $0.05/min orchestration fee than Retell's $0.07-$0.31/min range and genuine enterprise-scale proof (Amazon Ring evaluated 40+ vendors and now routes 100% of its inbound calls through it) — but it leans even further into pure code and API, without Retell's drag-and-drop conversation-flow builder.
Where it improves on Retell AI
- +Open models · YesOpen-weight models reach the pipeline through Groq, Together AI, Mistral, DeepSeek and OpenRouter, or a self-hosted server.Source ↗
- +On the command line · YesThe Vapi CLI covers assistants, numbers, calls, campaigns and logs from the terminal.Source ↗
- +Self-hosted · PartlySelf-serve is hosted only; on-premise is offered to large enterprises, and the orchestration layer otherwise never leaves Vapi.Source ↗
Trade-offs against Retell AI
- −Certifications · PartlySOC 2 Type II and a HIPAA BAA sit in the Scale contract, and the plan table shows SOC2 only in that column; HIPAA mode is a $2,000/month add-on on either plan.Source ↗
- 02
ElevenLabs Agents
Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM.
From FreeWhy it's on this listSwaps Retell's pure per-minute billing for subscription tiers with pooled minutes (Free through $990/month Business), built around best-in-class text-to-speech and instant voice cloning across 10,000+ voices — the pick if voice quality matters more than Retell's low-latency turn-taking pitch.
Where it improves on Retell AI
- +Agent permissions · YesTool use is gated per MCP server and per tool: always ask, fine-grained (auto-approved, requires approval, disabled), or no approval at all.Source ↗
- +Open models · YesOpen-weight models run two ways: ElevenLabs-hosted Qwen in the native model list, or Llama and Mixtral through a custom LLM endpoint such as Together AI, Groq or SambaNova.Source ↗
- +On the command line · YesA standalone CLI authenticates by OAuth and pushes, pulls and diffs agent, tool and test configurations held as files in version control.Source ↗
Trade-offs against Retell AI
- −In your editor · NoThe vendor enumerates its surfaces as web widgets, mobile apps, phone systems and custom integrations; no editor or IDE extension appears in that list.Source ↗
- −Getting out · PartlyAgents, tools and tests pull down as files via the CLI and conversations are readable over the API, but unused paid credits expire on cancel or downgrade and rollover caps at two months.Source ↗
- 03
PolyAI
Enterprise platform for building voice and chat agents that resolve customer calls, priced per minute.
Why it's on this listThe furthest departure: a pre-LLM-era enterprise incumbent (founded 2017, 200+ named customers, a $750M valuation) shipping SOC 2, HIPAA, GDPR and PCI DSS compliance plus a no-code Poly Agent Builder — sales-led only (a self-serve tier it briefly ran from May 2026 is gone as of an August 2026 re-check), unlike Retell's fully self-serve, sign-up-and-go pricing.
Where it improves on Retell AI
- +In your editor · YesThe ADK edits agent resources as local files in any editor, and Builder MCP plugs the same workflow into Cursor, Claude Code, Claude Desktop and Codex.Source ↗
- +On the command line · YesThe poly CLI pulls, branches, validates, pushes and chats against a project from the terminal.Source ↗
- +Free tier · YesSelf-serve sign-up at Agent Studio needs no sales call, and trial use is free of charge but evaluation-only, with limits set at PolyAI's discretion.Source ↗
Trade-offs against Retell AI
- −Multi-agent · NoThe only 'team of agents' feature is assigning several TTS voices to one agent; no coordination between multiple agents on a single task is documented, and the build assistant works one branch at a time.Source ↗
- −Pooled budget · PartlyConversation volume draws on one account-level Subscription Volume of CX Tokens, but the Wren builder allowance is per person and not shared.Source ↗
- −Getting out · PartlyTranscripts, recordings and metadata export via the Conversations API or a PolyAI-configured sync to your own S3 bucket, but unused CX Tokens expire each Contract Year and fees are non-refundable.Source ↗
- 04
Telnyx Voice AI Agents
Carrier-owned platform for phone and web voice agents, with telephony, STT, TTS, LLM and orchestration in one stack.
From $0.05/minuteWhy it's on this listOpen models · YesOpen-weight Qwen and Moonshot Kimi families run on Telnyx's own GPUs and are the recommended default for assistants, so prompt and response generation never leaves Telnyx infrastructure.Source ↗
Where it improves on Retell AI
- +On the command line · YesTwo terminal surfaces exist: a full resource-level Telnyx CLI and an Agent CLI whose composite commands stand up an assistant on a phone number in one invocation.Source ↗
- +Bring your own key · YesYou may bring your own LLM and TTS providers, storing third-party keys as integration secrets; ElevenLabs voices are explicitly billed on your own key rather than by Telnyx.Source ↗
Trade-offs against Retell AI
- −Done-for-you service · NoYou build and run the agent yourself in the portal or over the API; Telnyx sells platform capacity, and human help appears only as a dedicated account manager on the $500-minimum Committed plan, not as a build service.Source ↗
- −GPT · PartlyGPT models run as an external provider you supply credentials for: you create an OpenAI API key, store it as an integration secret and select the model, and OpenAI free-plan keys are rejected outright.Source ↗
- −Getting out · PartlyConversations, CDRs and usage reports are exportable by API or CSV and deletion can be requested within thirty days, but Telnyx says account configurations cannot be transferred and states no policy on unused balance.Source ↗
- 05
Cartesia
Real-time speech models and a managed runtime for production phone and web voice agents.
From FreeWhy it's on this listOn the command line · YesA `cartesia` CLI creates, deploys and manages agents, and can chat with agent logic locally.Source ↗
Where it improves on Retell AI
Trade-offs against Retell AI
- −Writes tests · NoThe evaluations framework scores live calls against metrics you define; it produces no test code.Source ↗
- −Done-for-you service · NoSelf-serve software: you build and deploy the agent yourself; sales contact exists for Enterprise terms, not for building it for you.Source ↗
- −Multi-agent · NoSystem tools enumerate three slots: end call, DTMF, and transfer to an E.164 phone number. An agent therefore hands off to a number, not to another Cartesia agent.Source ↗
- 06
AudioCodes Live Hub
Self-service cloud platform for building voice AI agents and connecting them to real telephony channels.
From $0.05/minuteWhy it's on this listOn the command line · PartlyAudioCodes ships no CLI of its own; terminal use is indirect, by pointing the Claude Code command-line agent at the platform's MCP endpoint with API client credentials.Source ↗
Where it improves on Retell AI
- +Bring your own key · YesYou may supply your own keys for both inference and speech: custom LLM providers are configured with your API key, and STT/TTS accounts can be brought in the same way.Source ↗
- +Seat model · PartlyThe platform itself is not sold per seat and imposes no user minimum; the only per-user charge is Microsoft Teams Direct Routing, billed monthly per enabled user.Source ↗
Trade-offs against Retell AI
- −Claude · PartlyClaude models are supported only as bring-your-own custom models configured with your own Anthropic API key; the pre-deployed model list carries OpenAI and Google models only.Source ↗
- −In your editor · NoThere is no editor or IDE extension: authoring happens in the web portal, and the only documented developer-tool integrations are the two MCP clients named below.Source ↗
- −Getting out · PartlyCall records, recordings, transcripts and AI agent logs can be exported from the portal or the API, but they are deleted automatically at the retention period and no credit-refund terms are published.Source ↗
Side by side
Compare Retell AI with the shortlist
Compare alternatives to Retell AI
Pick up to three alternatives to see how they differ from Retell AI.
The digest
Which agents actually ship. New agents and articles, by email, at most once a week.
Advertisement
Reach buyers choosing an agent. Billed monthly. Cancel anytime.
See ad options →Featured · top of your category →The digestFree
Which agents actually ship.
New agents and articles, by email, at most once a week.
One-click unsubscribe