US PRODUCT RESEARCH

Retell AI

A voice-agent platform with phone and web deployment, conversation flows, tools, simulation testing and call monitoring.

Checked Oct 15, 2026 · 11 official sources · Desk research

AI voice agents

A GOOD FIT WHEN

Teams building production phone agents who want a packaged voice stack and measurable testing workflow.

Phone/SIP and web deployment
Warm transfer and business-system connections
Simulation, versioning and live-call monitoring

LOOK MORE CLOSELY WHEN

You plan to budget from the lowest advertised minute rate without model, voice, telephony and add-ons.

Total rate changes by model, voice and optional features
Telephony and post-transfer usage can remain billable
Enterprise security and implementation terms need a scoped agreement

CATEGORY-SPECIFIC EVIDENCE

Capabilities, controls and depth.

Scores combine core capabilities and workflow depth. Full support earns full points; limited support earns half. Unverified features create a range, and paid-plan requirements are shown in the evidence. How scoring works →

AI voice agents · 28 features

80–99/100 documented fit

Core capabilities32 / 32 pts10/10 checks with established status

Workflow depth47.9–66.8 / 68 pts12/18 checks with established status

Show checksShowing fewer rows does not change the score.

AI voice agents · 28 weighted capability checks
Feature / weight	Support, evidence & points
Core capabilityTelephone deploymentDeploy an agent to a documented phone or voice-calling channel. 4 points maximum	Supported4 / 4 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Core capabilityWeb voice or SIP connectionDeploy voice through a browser interface or connect telephony using SIP. 4 points maximum	Supported4 / 4 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Depth checkConfigured live-call transferConfigure a production call transfer to a person or destination with observable transfer behavior. 5.6 points maximum Ask for a demonstration Make a test phone call and transfer it to the configured human destination. A scenario to run with the supplier; not a completed product test.	Supported5.6 / 5.6 pts Transfer tools support human warm-transfer context. Official documentation · Oct 15, 2026Source
Depth checkFallback when call setup or agent failsConfigure fallback handling when the voice agent or its telephony connection cannot serve a call. 6.4 points maximum Ask for a demonstration Demonstrate the configured fallback for an unavailable agent or destination. A scenario to run with the supplier; not a completed product test.	Not verified0–6.4 / 6.4 pts This specific workflow has not been established by the reviewed evidence. Not verified · Oct 15, 2026Source
Core capabilityLive business actionsCall a tool, webhook or API during a conversation. 4 points maximum	Supported4 / 4 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Core capabilityHuman or specialist handoffTransfer a conversation to a human or another configured specialist. 4 points maximum	Supported4 / 4 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Depth checkStructured action argumentsDefine tool parameters or structured fields so a business action receives inspectable values. 5.6 points maximum Ask for a demonstration Call a booking or CRM tool and inspect the arguments sent for the requested action. A scenario to run with the supplier; not a completed product test.	Supported5.6 / 5.6 pts Custom tools define typed parameters and authentication headers separately. Official documentation · Oct 15, 2026Source
Depth checkContext-preserving handoffPass conversation context or a summary to the next agent or human during a handoff. 6.4 points maximum Ask for a demonstration Transfer a call after collecting information and show what the receiving person or agent receives. A scenario to run with the supplier; not a completed product test.	Supported6.4 / 6.4 pts Transfer tools support human warm-transfer context. Official documentation · Oct 15, 2026Source
Core capabilityPre-launch agent testingTest agent conversations before sending production traffic. 3.2 points maximum	Supported3.2 / 3.2 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Core capabilityCall logs and monitoringInspect call records, transcripts or operational analytics. 3.2 points maximum	Supported3.2 / 3.2 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Depth checkRepeatable scenario testingRun saved or generated test scenarios with outcomes or evaluation results. 4.8 points maximum Ask for a demonstration Run the same successful and failing scenarios after a prompt change and inspect the results. A scenario to run with the supplier; not a completed product test.	Supported4.8 / 4.8 pts Simulation cases are rerunnable and graded against success criteria. Official documentation · Oct 15, 2026Source
Depth checkVersioned agent changesInspect prior agent configurations and restore or select a previous version. 4.8 points maximum Ask for a demonstration Change an agent instruction, then show how to return production to its earlier version. A scenario to run with the supplier; not a completed product test.	Supported4.8 / 4.8 pts Published versions and environment tags select the production configuration. Official documentation · Oct 15, 2026Source
Core capabilityDeveloper APIs or webhooksManage agents or exchange conversation data using programmable interfaces. 2.4 points maximum	Supported2.4 / 2.4 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Core capabilityBusiness or telephony connectorsUse supplied CRM, calendar, contact-center or telephony integrations. 2.4 points maximum	Supported2.4 / 2.4 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Depth checkAuthenticated business-tool accessConfigure authentication or protected credentials for calling an external business tool. 3.2 points maximum Ask for a demonstration Show a business tool connection with its credentials separated from the spoken conversation. A scenario to run with the supplier; not a completed product test.	Supported3.2 / 3.2 pts Custom tools define typed parameters and authentication headers separately. Official documentation · Oct 15, 2026Source
Depth checkStructured post-call event exportSend or retrieve post-call structured results and call identifiers through an API or webhook. 4 points maximum Ask for a demonstration Finish a test call and inspect its structured results in an external system. A scenario to run with the supplier; not a completed product test.	Supported4 / 4 pts Structured extraction results are accessible through call_analyzed events or Get Call. Official documentation · Oct 15, 2026Source
Core capabilityBusiness knowledge groundingProvide business documents, website information or a knowledge source for answers. 2.4 points maximum	Supported2.4 / 2.4 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Core capabilityConfigurable conversational behaviorConfigure agent instructions, dialogue paths or model behavior. 2.4 points maximum	Supported2.4 / 2.4 pts US numbers, SIP/web voice, tools, tests and knowledge. Official documentation · Oct 15, 2026Source
Depth checkManage and refresh grounded knowledgeUpdate or replace business knowledge used by the conversational agent and inspect its configured source. 3.2 points maximum Ask for a demonstration Change a policy in a knowledge source and demonstrate how the agent’s source is refreshed. A scenario to run with the supplier; not a completed product test.	Supported3.2 / 3.2 pts Knowledge sources and indexing can be managed per agent. Official documentation · Oct 15, 2026Source
Depth checkExplicit action or escalation boundariesConfigure a rule that restricts the agent’s permitted action or escalates an out-of-scope request. 4 points maximum Ask for a demonstration Ask for a restricted action and show the configured refusal or human escalation. A scenario to run with the supplier; not a completed product test.	Supported4 / 4 pts Guardrails configure prohibited-content detection and replacement behavior. Official documentation · Oct 15, 2026Source
Depth checkConfigure backup speech-synthesis providersDemonstrate "Configure backup speech-synthesis providers" with test data. Show the result, an exception case, and the required plan. 2.5 points maximum Ask for a demonstration Demonstrate "Configure backup speech-synthesis providers" with test data. Show the result, an exception case, and the required plan. A scenario to run with the supplier; not a completed product test.	Supported2.5 / 2.5 pts Retell documents fallback to another TTS provider after provider failure. Product changelog documents feature; confirm current compatible voice models and local contract. Official documentation · Oct 21, 2026Source
Depth checkConfigure backup speech-recognition providersDemonstrate "Configure backup speech-recognition providers" with test data. Show the result, an exception case, and the required plan. 2.5 points maximum Ask for a demonstration Demonstrate "Configure backup speech-recognition providers" with test data. Show the result, an exception case, and the required plan. A scenario to run with the supplier; not a completed product test.	Not verified0–2.5 / 2.5 pts This specific check has not been verified. Missing evidence does not mean the capability is absent. Ask for a demonstration in the proposed plan. Not verified · Oct 21, 2026Source
Depth checkSet custom pronunciation for names and termsSet a custom pronunciation for a sample name. Compare two supported voice models and show any model or language limitations. 2.5 points maximum Ask for a demonstration Set a custom pronunciation for a sample name. Compare two supported voice models and show any model or language limitations. A scenario to run with the supplier; not a completed product test.	Limited1.3 / 2.5 pts Custom pronunciation accepts word, phonetic alphabet and pronunciation values. Pronunciation support is voice/model-dependent; availability must be demonstrated for selected language/model. Official documentation · Oct 21, 2026Source
Depth checkInspect latency by voice-pipeline componentDemonstrate "Inspect latency by voice-pipeline component" with test data. Show the result, an exception case, and the required plan. 2.5 points maximum Ask for a demonstration Demonstrate "Inspect latency by voice-pipeline component" with test data. Show the result, an exception case, and the required plan. A scenario to run with the supplier; not a completed product test.	Not verified0–2.5 / 2.5 pts This specific check has not been verified. Missing evidence does not mean the capability is absent. Ask for a demonstration in the proposed plan. Not verified · Oct 21, 2026Source
Depth checkConfigure reminders after caller silenceDemonstrate "Configure reminders after caller silence" with test data. Show the result, an exception case, and the required plan. 2.5 points maximum Ask for a demonstration Demonstrate "Configure reminders after caller silence" with test data. Show the result, an exception case, and the required plan. A scenario to run with the supplier; not a completed product test.	Not verified0–2.5 / 2.5 pts This specific check has not been verified. Missing evidence does not mean the capability is absent. Ask for a demonstration in the proposed plan. Not verified · Oct 21, 2026Source
Depth checkChoose a separate action when voicemail answersDemonstrate "Choose a separate action when voicemail answers" with test data. Show the result, an exception case, and the required plan. 2.5 points maximum Ask for a demonstration Demonstrate "Choose a separate action when voicemail answers" with test data. Show the result, an exception case, and the required plan. A scenario to run with the supplier; not a completed product test.	Supported2.5 / 2.5 pts Voicemail handling can hang up, leave a recorded message or generate a personalized message. Product changelog; detection is not guaranteed and local outbound-calling permissions remain separate. Official documentation · Oct 21, 2026Source
Depth checkRedact sensitive fields from call transcriptsDemonstrate "Redact sensitive fields from call transcripts" with test data. Show the result, an exception case, and the required plan. 2.5 points maximum Ask for a demonstration Demonstrate "Redact sensitive fields from call transcripts" with test data. Show the result, an exception case, and the required plan. A scenario to run with the supplier; not a completed product test.	Not verified0–2.5 / 2.5 pts This specific check has not been verified. Missing evidence does not mean the capability is absent. Ask for a demonstration in the proposed plan. Not verified · Oct 21, 2026Source
Depth checkVerify cryptographic post-call webhook signaturesDemonstrate "Verify cryptographic post-call webhook signatures" with test data. Show the result, an exception case, and the required plan. 2.5 points maximum Ask for a demonstration Demonstrate "Verify cryptographic post-call webhook signatures" with test data. Show the result, an exception case, and the required plan. A scenario to run with the supplier; not a completed product test.	Not verified0–2.5 / 2.5 pts This specific check has not been verified. Missing evidence does not mean the capability is absent. Ask for a demonstration in the proposed plan. Not verified · Oct 21, 2026Source

Compare in AI voice agents →

AI CAPABILITY CHECK

What does its AI actually do?

Native AI capabilities

Configurable real-time speech agents use prompts or conversation flows, knowledge retrieval and tools to complete tasks or transfer to humans.

Official AI source

Documented capabilities

Conversational phone handling
Knowledge-grounded answers and tool actions
Warm handoff and structured post-call extraction

Limits to check

Actual task success needs a use-case pilot
AI can misinterpret speech or business data; configure fallback and supervision

Understand the full price

Published AI voice range is $0.07–$0.31/minute, depending on configuration. Telephony and selected add-ons are additional; the full model/voice menu can exceed the headline range.

Billing basis: usage. Unit: per configured conversation minute. Currency: USD.

US telephony
Model/voice choice
Knowledge base and QA add-ons
Extra concurrency

Verify current pricing with the vendor

Integrations and deployment

SIP telephony
Salesforce
HubSpot
Webhooks/API

Confirm the applicable data-processing terms, account roles, retention settings, and security documentation for the selected plan before production use.

US buying context

US number and telephony pricing is documented. Validate caller location, number ownership, recording choices and permitted outbound use with the implementation team.

The evidence record

Pay-as-you-go includes twenty concurrent calls

Official evidence

The stack has multiple billable components

Official evidence

Warm transfer and web calling are documented

Official evidence

Simulation tests can catch regressions

Official evidence

API/webhooks and CRM data sync are documented

Official evidence

Source library

Research is based on documentation, not a hands-on performance test. Report a correction.

EXPLORE THE ALTERNATIVES

Keep your options open.

AI voice agents alternatives · highest documented score first.

74–100/100 documented fit

ElevenLabs Agents

Voice and multimodal agents with speech models, workflows, knowledge retrieval, tools, telephony and application SDKs.

Good fit forTeams building branded voice experiences across phone, web or mobile with a configurable tool layer.

$6.00per month

View research

71–100/100 documented fit

Vapi

Developer-oriented voice-agent infrastructure with configurable speech/model providers, tools, assistants and multi-agent handoffs.

Good fit forEngineering teams that want to control models, tools, deployment and application behavior.

$0.05per minute hosting only

View research

66–100/100 documented fit

Synthflow

Enterprise voice-agent deployment sold with scoped capacity, integrations, telephony and launch support.

Good fit forOrganizations buying a supported production voice rollout with defined commercial and operational terms.

$30,000.00per year, starting contract · billed annually

View research