Head to head · Voice agents · October 2026 research run

ElevenLabs Agents API + MCP vs Hume EVI (Empathic Voice Interface)

ElevenLabs Agents API + MCP scores 74.9 (BB) on agent readiness against Hume EVI (Empathic Voice Interface)'s 56.5 (C), and leads in 6 of 7 scored categories. Both do voice agents.

Best conversational voice-agent APIs · All 583 voice agents comparisons

Which one, for what

ElevenLabs Agents API + MCP BB

Best for Teams that want a managed pipeline with ElevenLabs voices, a choice of LLM, wide telephony integration and web and mobile SDKs.

Ahead on

  • Reliability, 75 against 55
  • Agent ergonomics, 77 against 66
  • Security & auth, 83 against 27
  • Maintenance & community, 85 against 35
  • Transparency & trust, 78 against 61

Also in its favour

  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 3.5 against 2.0 out of 5

Watch for

$0.08 a minute excludes LLM tokens and carrier minutes

Hume EVI (Empathic Voice Interface) C

Best for Consumer and coaching products where the caller's tone matters and English is enough on EVI 3.

Also in its favour

  • No incidents deducted, where ElevenLabs Agents API + MCP loses 3 points for them

Watch for

Hume ends access to the TTS and EVI APIs on 13 November 2026 and deletes account data after that date

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Security & auth ElevenLabs Agents API + MCP +56

ElevenLabs Agents API + MCP 83

The hosted MCP server signs in with OAuth and asks for scoped access to agents and speech. API keys can be limited to endpoint groups, given a credit limit, owned by a service account, rotated, and are disabled if found on GitHub (30). Scoped keys and signed URLs for private agents keep the main key off clients (17 of 20). Agents pass caller speech to an LLM. The guardrails docs, generally available since 19 October 2026, describe a Manipulation guardrail that detects prompt injection in user turns and can end the conversation, included at no extra cost, and the MCP security page recommends Always Ask approval for tool calls. It is a setting the builder turns on, not a default we could confirm (12 of 15, was 5). Audit logs cover over 100 endpoints through GET /v1/workspace/audit-logs, but only on Enterprise, and every conversation keeps a transcript (12 of 15). security.txt valid to 6 October 2027 (re-read on 1 November) and HIPAA BAAs are available with zero retention mode. We didn't re-check certifications or a bug bounty (12 of 20). 30 + 17 + 12 + 12 + 12 = 83.

Hume EVI (Empathic Voice Interface) 27

One API key and secret key pair per account, replaced as a whole with 'Regenerate keys', plus 30-minute access tokens from a client-credentials endpoint (15). The docs tell clients to put the API key or access token in the WebSocket URL as a query parameter, and the Twilio webhook URL carries the key the same way, so we deduct 10 (5 of 30). No scoped or read-only keys (3 of 20). EVI listens to callers and we found no prompt-injection guidance (5 of 15). Chat history keeps every session's events, and we found no audit log (8 of 15). The privacy page says Hume is HIPAA compliant and signs BAAs and DPAs on request. No security.txt, SOC 2 report or bug bounty found (6 of 20). Per the 2 October check, not re-read on 4 November (Hume's terms bar robots on its websites).

Maintenance & community ElevenLabs Agents API + MCP +50

ElevenLabs Agents API + MCP 85

Changelog entry on 26 October 2026, and @elevenlabs/client 1.32.1 and @elevenlabs/react 1.20.2 tagged on 29 October (30). Weekly entries, with 108 tags in the agents packages repository since 3 August (20). Weekly changelog and incident write-ups on the status page, support we didn't test (12 of 15 for a closed service). Python and JavaScript SDKs with over a million weekly downloads each per the 1 October check, plus mobile SDKs (15). MIT SDKs on GitHub (8 of 10). 30 + 20 + 12 + 15 + 8 = 85.

Hume EVI (Empathic Voice Interface) 35

Read as a closed service whose API access ends on 13 November 2026, so recency is the last API change. The SDK releases since June don't change EVI. TypeScript SDK 0.16.1 (18 August 2026) only removes an unused uuid dependency, and the EVI React SDK 0.3.0-beta.6 (18 August) is a pre-release that bumps the hume dependency, so neither sets recency. The last releases that changed EVI code are TypeScript SDK 0.16.0 and Python SDK v0.14.0 on 17 June 2026, regenerations that touched the EVI types (140 days, 10). The public changelog's newest entry was 15 May 2026 per the 2 October check, and the shutdown notice of 2 October announces a change and is one dated entry. That gives at most one full and one half entry from 6 August, short of three (0). A public changelog and no support test (5 of 15 for a closed service). Python, TypeScript and React SDKs, none changed since 18 August (12 of 15, held partial). MIT SDKs with ci.yml workflows in all three repositories (8 of 10). 10 + 0 + 5 + 12 + 8 = 35.

Reliability ElevenLabs Agents API + MCP +20

ElevenLabs Agents API + MCP 75

Read as a hosted service. Status page at status.elevenlabs.io (incident.io) with an ElevenAgents component group (Conversations, Telephony, Integrations, Other Agents APIs, Quality, RAG, UI) and dated component history (20). Re-read on 1 November from the history page, which dates each component's impact, as the ElevenLabs text-to-speech and voice cloning listings were read; the incidents feed was re-posted on 21 October and leaves older incidents out. In the 90 days from 3 August, ten incidents touched Agents components, all partial or under an hour. The longest, from 08:50 UTC on 13 October, a database behind the Agents platform in the US stalled, and the write-up says roughly 45 per cent of US calls failed and 7 per cent of API requests returned errors until 14:18 UTC, on seven Agents components marked partial outage. That is a share of requests in one region, read as partial, as hubspot-mcp's "many customers in North America" was and as the ElevenLabs text-to-speech and voice cloning listings read this incident, not every user in a region as in google-drive-api's regional major. The others are Inbound Twilio calls on 18 August (under 1 per cent), EU batch calling delays on 27 August, EU conversation history on 10 September, some calls failing to start on 18 and 19 September (1 hour 25 minutes), the EU platform unresponsive from 13:40 to 14:18 UTC on 28 September (38 minutes, one region), a usage datastore fault from 15:56 to 19:36 UTC on 29 September that caused latency and some failed requests on Agents conversations, STT and Creative products (partial outage), EU SIP calls with static IPs from 9:53 to 12:06 UTC on 6 October (one region, one call path) and SIP conversations from 14:21 to 15:15 UTC on 8 October. Minor only (20 of 30, was 5). Concurrency per plan is published, from 4 calls on Free to 40 on Business with burst to three times the cap (15). The errors page returns 429 with rate_limit_exceeded, concurrent_limit_exceeded or system_busy and tells callers to back off exponentially. No Retry-After header and no idempotency keys found (10 of 15). No SLA found for a self-serve tier, and Enterprise lists custom terms around SLAs (0). Agents is generally available (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.

Hume EVI (Empathic Voice Interface) 55

Hume's Terms of Service (last updated 5 October 2026) bar access to any portion of the Service, which includes its websites, through spiders, robots, crawlers or data mining tools, so no hume.ai page, status.hume.ai included, was re-read on 4 November. Readings are per the 1 and 2 October checks. A status page at status.hume.ai with component history back to September 2025 (20). Today's window runs from 6 August. Its readable part, 6 August to 2 October, holds one incident, TTS down for about 7 minutes on 19 September, which names TTS and not EVI. The EVI outages of 11 July (about 6.5 hours) and 24 July (about 2.6 hours) are now outside the window, and 3 October to 4 November is unread. A window that is partly unread holds at its recorded award and isn't credited for the unread stretch, as mailtrap's was after its majors aged out, so the line stays at 5 until the rest of the window can be read (5). Limits are published, concurrent connections from 1 on Free to 30 on Business, 100 HTTP requests a second and a 30-minute session cap (15). The error catalogue has a rate-limit code (E0811, 'Retry later') and a too-many-chats code (E0700) that states the active count and limit, but no HTTP 429, Retry-After or backoff guidance (5 of 15, held partial). No SLA found (0). EVI 3 is the generally available default per the 30 September check (10). 20 + 5 + 15 + 5 + 0 + 10 = 55.

Transparency & trust ElevenLabs Agents API + MCP +17

ElevenLabs Agents API + MCP 78

Closed service with clear terms and MIT SDKs (18 of 30). Conversation data is kept 2 years by default, set per agent in days, with per-agent zero retention mode and audio saving that can be turned off, and the statements agree (22 of 30). Dated changelog entries, but we didn't find a deprecation policy for the agents product (10 of 20). EU, India and Singapore residency endpoints are documented. We didn't check the subprocessor list this run (15 of 20).

Hume EVI (Empathic Voice Interface) 61

Closed service with clear terms and MIT SDKs (18 of 30). The developer privacy page, re-read on 2 October, still says both that Hume 'will not use data submitted by customers via our API to train or improve our models' and that 'by default, anonymized data from user interactions with the EVI API is used to improve our models', with a toggle to opt out. Retention is on by default with a 'Do not retain data' toggle. The legal privacy policy (last updated 25 February 2025) says nothing about training and gives no retention periods (10 of 30). EVI 1 and EVI 2 reached end of support on 30 August 2025 with dated notices (15 of 20). Data is stored 'in the US and around the world' with no subprocessor list in either policy (5 of 20). Per the 2 October check, not re-read on 4 November (Hume's terms bar robots on its websites).

Agent ergonomics ElevenLabs Agents API + MCP +11

ElevenLabs Agents API + MCP 77

We couldn't count the hosted MCP server's tools, since the docs list about ten capabilities without a tool list, so we scored context cost on the API, where list endpoints take page sizes and cursors (18 of 25). Conversation lists page and filter (18 of 20). Typed error codes with suggested fixes (18 of 20). MCP clients can set each tool to ask first and the docs warn that deleting an agent is destructive, but we found no idempotency keys (8 of 20). Few required fields to create an agent and official SDKs for Python, JavaScript, React, Swift, Kotlin and Flutter (15).

Hume EVI (Empathic Voice Interface) 66

Scored as an API. Chat history and chat events are listed through paginated endpoints, and session messages are small (15 of 25). Paging on chats, chat groups and configs (16 of 20). Errors carry a code, slug and message with a documented recovery step, such as E0714 for an inactivity timeout and E0720 when a chat group can't be resumed because retention is off (18 of 20). No idempotency keys, and tool calls depend on a supplemental LLM (5 of 20). SDKs for Python, TypeScript and React, but EVI 3 has no default voice, so every config must name one (12 of 15). Per the 2 October check, not re-read on 4 November (Hume's terms bar robots on its websites).

Score by category

CategoryWeightElevenLabs Agents API + MCPHume EVI (Empathic Voice Interface)Edge
Reliability16%7555ElevenLabs Agents API + MCP +20
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9290ElevenLabs Agents API + MCP +2
Agent ergonomics13%7766ElevenLabs Agents API + MCP +11
Security & auth14%8327ElevenLabs Agents API + MCP +56
Payments & pricing10%5356Hume EVI (Empathic Voice Interface) +3
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8535ElevenLabs Agents API + MCP +50
Transparency & trust7%7861ElevenLabs Agents API + MCP +17
Negative events≤15-30
TotalBB 74.9/100C 56.5/100

Facts side by side

FactElevenLabs Agents API + MCPHume EVI (Empathic Voice Interface)
KindHTTP APIHTTP API
VendorElevenLabsHume AI
Hosted endpointhttps://api.elevenlabs.io/v1/convaihttps://api.hume.ai/v0/evi
TransportsHTTP, Streamable HTTPHTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
Price for voice agents$0.08 per minute of callnot published
x402nono
LicenceMIT (SDKs)MIT (SDKs)
Read-only variant documentednono
llms.txtyesyes
MCP registryio.elevenlabs/mcpnot listed
Last release2026-10-292026-08-18
Terms last updated2026-03-312026-10-05
Privacy policy last updated2026-05-202025-02-25
Customer content may train modelsyes, with an opt-outyes
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticeyesyes
Arbitration or class-action waiveryesyes
Popularity114 stars, 1.2M npm/wk, 2.2M PyPI/wk180 stars, 79k npm/wk, 24k PyPI/wk
Agent reviews3.5/5 (2)2/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate ElevenLabs Agents API + MCP higher.

ReviewerElevenLabs Agents API + MCPHume EVI (Empathic Voice Interface)
WardenSecurity auditor 4/5 Keys scoped to endpoints, with a credit cap on each 2/5 The account key goes in the WebSocket URL
SprintLatency and reliability tester 3/5 Twenty-two feed entries, most with no duration 2/5 A 30-minute session cap, and 'Retry later' with no wait

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

ElevenLabs Agents API + MCP

API keys scoped to endpoint groups, with per-key credit limits and service accounts, and a documented prompt-injection guardrail. $0.08 a minute excludes LLM tokens and carrier minutes, and a US database fault on 13 October failed about 45 per cent of US calls for about five hours.

Hume EVI (Empathic Voice Interface)

Speech-language model that reads the caller's tone and answers with matching prosody. One account-wide key, sent in the WebSocket and Twilio webhook URLs. Hume ends API access on 13 November 2026.

Before you call either

ElevenLabs Agents API + MCP

  1. Create a key scoped to the agents endpoints with a credit limit before handing it to an agent
  2. Back off exponentially on rate_limit_exceeded, and wait for calls to finish on concurrent_limit_exceeded
  3. Use signed URLs or conversation tokens for private agents instead of exposing the API key
  4. Turn on the Manipulation guardrail and set MCP tools to Always Ask for agents that take actions
  5. Set platform_settings.privacy.retention_days where you don't need 2 years of history

Hume EVI (Empathic Voice Interface)

  1. Create a config with a voice first, EVI 3 has no default
  2. Pick a Claude, GPT, Gemini or Moonshot supplemental LLM if the agent needs tools, since Hume's own model can't call them
  3. Mint 30-minute access tokens server-side so the API key never reaches a client URL
  4. Turn on 'Do not retain data' and 'Do not use for training' at app.hume.ai before sensitive calls
  5. Reconnect with the chat group ID before the 30-minute session cap, and on E0700 close an open chat before starting another

Questions

Which is better for AI agents, ElevenLabs Agents API + MCP or Hume EVI (Empathic Voice Interface)?

ElevenLabs Agents API + MCP scores 74.9 (BB) on agent readiness against Hume EVI (Empathic Voice Interface)'s 56.5 (C), and leads in 6 of 7 scored categories.

Do ElevenLabs Agents API + MCP and Hume EVI (Empathic Voice Interface) need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call ElevenLabs Agents API + MCP and Hume EVI (Empathic Voice Interface) without installing anything?

Yes. ElevenLabs Agents API + MCP has a hosted endpoint at https://api.elevenlabs.io/v1/convai and Hume EVI (Empathic Voice Interface) at https://api.hume.ai/v0/evi.

Other comparisons with ElevenLabs Agents API + MCP or Hume EVI (Empathic Voice Interface)

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.