◎ Discry Score
elevenlabs.com
ai · API
A
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 99 (A)
Discry your API →
AI · RANK #7 OF 43

ElevenLabs is Agent-Ready to agents.

Discry independently scored how well an AI agent can discover and understand the ElevenLabs API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 95/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Pass
llms-full.txtA full-text bundle agents can load in one request.Pass
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Pass
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Pass
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Pass
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 96/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Pass
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Pass
Error-recovery guidanceDocumented failure modes and how to recover from them.Partial
Answer-first formatThe answer leads; preamble does not bury it.Pass
Capability boundariesClear limits — what the API can and cannot do.Pass
Naming consistencyConsistent, predictable naming across endpoints.Pass
Heading hierarchyClean heading structure agents can navigate.Pass
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Pass
Token efficiencyDocs are concise enough to fit an agent context window.Pass

What we found

  • ElevenLabs achieves the highest Discry score in this batch (92/100) through near-complete agent infrastructure: public OpenAPI spec, well-structured llms.txt, LLM-optimized llms-full.txt, official MCP server on all registries, and AGENTS.md.
  • An agent discovering ElevenLabs would find explicit welcome signals: Content-Signal header (ai-train=yes, ai-input=yes), the llms.txt explicitly links to 'LLM-optimized' full documentation, and the OpenAPI spec is at the standard path.
  • The llms.txt quality is exceptional — it functions as a structured product catalog with API-focused descriptions for every capability (TTS, STT, voice cloning, music, sound effects, dubbing, agents).
  • An agent building voice applications would find complete workflow documentation: ElevenAgents for conversational AI, ElevenAPI for direct access, and ElevenCreative for content generation — all clearly delineated.
  • The only discovery gap is .well-known/mcp.json — trivial to add given the official MCP server already exists and is registered everywhere.

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Add .well-known/mcp.json pointing to the official ElevenLabs MCP server — the only missing piece in an otherwise near-perfect discovery stack.
  2. 02Add explicit error recovery documentation for common API failures: quota exceeded, voice not found, audio format incompatibility, WebSocket connection drops.
  3. 03Consider reducing llms-full.txt size or offering a tiered version (llms-api.txt at <50KB for quick agent orientation vs full 2MB for deep integration).
  4. 04Document idempotency patterns for TTS generation to help agents safely retry failed requests without generating duplicate audio.
  5. 05Add the MCP server create endpoint documentation (already at elevenlabs.io/docs/api-reference/mcp/create) to the llms.txt for agent discoverability.

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

API Key (xi-api-key header)✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Well-documented API with API key auth. OpenAPI spec publicly accessible at both elevenlabs.io/openapi.json and api.elevenlabs.io/openapi.json. Supports HTTP and WebSocket for streaming. Rate limits tied to subscription tier with character quotas. Official Python and Node.js SDKs.

See your own Discry Score.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free