{"slug":"retell-ai","url":"https://www.altairalabs.ai/vs/retell-ai/","markdown":"https://www.altairalabs.ai/vs/retell-ai.md","name":"Retell AI","vendor":"Retell AI","category":"Customer service and voice","checked":"2026-10-22","summary":"Omnia runs recorded duplex voice tests on every release, gates on them, and rolls out in steps. Retell’s batch tests simulate the call as text, so timing problems only show up on a web call made by hand.","headline":"Retell versions and tests voice agents, and Omnia tests them the way a caller hears them, as audio.","scene":{"setup":"A new prompt passes every batch test.","omnia":"On Omnia it also has to pass a set of calls, including a caller who goes quiet to find a card. The new prompt starts talking again before they’re back, so the version stays at the gate.","omniaCaps":["voice-testing","deploy-gate"],"them":"Simulation runs as a text conversation. Voice is tested with manual web calls, and agents using a custom LLM aren’t supported in simulation.","source":"https://docs.retellai.com/test/llm-simulation-testing","omniaEvidence":"https://promptarena.altairalabs.ai/arena/how-to/voice/setup-voice-testing/"},"differences":[{"title":"Tests that make the call","body":"Voice scenarios run as duplex audio on every version. Each call is recorded for playback.","caps":["voice-testing","duplex-voice"],"them":"Automated simulation is text; voice is tested by hand.","source":"https://docs.retellai.com/test/test-overview","omniaEnterprise":false,"omniaEvidence":"https://promptarena.altairalabs.ai/arena/how-to/voice/setup-voice-testing/"},{"title":"Rollback on a slice of calls","body":"A version that passes the suite takes calls in steps, and Omnia moves traffic back if its metrics drop. Callers already on the line finish on the version they started with.","caps":["deploy-gate","progressive-rollout","sticky-sessions","metric-gated-promotion"],"them":"Published versions are read-only with prod and staging tags; rolling back means moving the tag. Automatic rollback isn’t documented.","source":"https://docs.retellai.com/agent/version","omniaEnterprise":true,"omniaEvidence":"https://promptarena.altairalabs.ai/arena/how-to/interfaces/run-in-ci/"},{"title":"Tests that can’t book a real appointment","body":"Tests run against the tools in an environment you choose, and tool-call assertions check what the agent did. Policy on every call refuses anything you haven’t allowed.","caps":["tool-assertions","tool-testing","per-call-policy"],"them":"Unmocked functions call their real endpoints during simulation, and MCP tools ignore mocks.","source":"https://docs.retellai.com/test/llm-simulation-testing","omniaEnterprise":true,"omniaEvidence":"https://promptarena.altairalabs.ai/arena/reference/assertions/"}],"rows":[{"topic":"Immutable versions","omnia":"A versioned pack.","caps":["gitops-sync"],"them":"Read-only published versions.","coverage":"yes","source":"https://docs.retellai.com/agent/version","omniaEnterprise":false,"omniaEvidence":"https://omnia.altairalabs.ai/reference/core/promptpacksource/"},{"topic":"Batch regression tests","omnia":"Yes, and they gate the release.","caps":["selfplay","deploy-gate"],"them":"Batch tests with an API.","coverage":"yes","source":"https://docs.retellai.com/test/batch-test-simulation","omniaEnterprise":false,"omniaEvidence":"https://promptarena.altairalabs.ai/arena/explanation/scenario-design/"},{"topic":"Automated voice tests","omnia":"Barge-in, overlap, dead air.","caps":["voice-testing"],"them":"Text simulation only.","coverage":"undocumented","source":"https://docs.retellai.com/test/llm-simulation-testing","omniaEnterprise":false,"omniaEvidence":"https://promptarena.altairalabs.ai/arena/how-to/voice/setup-voice-testing/"},{"topic":"Adversarial callers","omnia":"Yes.","caps":["adversarial"],"them":"Not documented.","coverage":"undocumented","source":"https://docs.retellai.com/test/test-overview","omniaEnterprise":false,"omniaEvidence":"https://promptarena.altairalabs.ai/arena/how-to/voice/voice-red-team/"},{"topic":"Stepped rollout, auto rollback","omnia":"Yes.","caps":["progressive-rollout"],"them":"A/B split across agents.","coverage":"partly","source":"https://docs.retellai.com/deploy/ab-testing","omniaEnterprise":false,"omniaEvidence":"https://omnia.altairalabs.ai/tutorials/progressive-rollouts/"},{"topic":"PII redaction","omnia":"Sessions and memory.","caps":["pii-sessions","pii-memory"],"them":"Per-minute add-on.","coverage":"yes","source":"https://www.retellai.com/pricing","omniaEnterprise":true,"omniaEvidence":"https://omnia.altairalabs.ai/how-to/privacy/configure-privacy-policies/"},{"topic":"Runs in your infrastructure","omnia":"Yes.","caps":["workspaces"],"them":"Not documented.","coverage":"undocumented","source":"https://www.retellai.com/pricing","omniaEnterprise":false,"omniaEvidence":"https://omnia.altairalabs.ai/how-to/workspaces/manage-workspaces/"}],"faq":[{"q":"How is each priced?","a":"Retell charges per minute, with add-ons such as PII removal priced per minute too. Omnia has no per-minute meter: free while you build, the core free in production, and an enterprise licence per environment per year from £30,000."}]}