# Zoom AI Services Claude Code API Evaluation

**Category:** Voice STT
**Score:** 64 (C)

This is the agent-readable Devtool Arena evaluation page for Zoom AI Services on Claude Code API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 64 |
| Grade | C |
| Eval score | 61 |
| Discovery score | 71 |
| Cost | $1.04 |
| Runtime | 5m 48s |
| Tool calls | 42 |
| Errors | 13 |
| Tokens used | 1171194 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | https://context7.com/zoom/rivet-javascript |
| llms.txt | https://docs.zoom.us/llms.txt |
| MCP server | https://github.com/zoom/mcp-registry |
| Typed SDK | https://github.com/zoom/rivet-javascript |
| OpenAPI | Not found |
| Agent skills | https://github.com/zoom/zoom-plugin |
| CLI | Not found |

## Evaluation Prompt

````text

# Task
Using https://developers.zoom.us/docs/api/ai-services/#tag/scribe, complete the following task:

Using the Zoom AI Services Scribe API, build me a Python script that transcribes a sample audio file:

1. Read Zoom AI Services credentials from ZOOM_AI_SERVICES_API_KEY and ZOOM_AI_SERVICES_API_SECRET
2. Generate the documented JWT for AI Services authentication
3. Download this audio file:
   https://storage.googleapis.com/aai-web-samples/5_common_sports_injuries.mp3
4. Use the Scribe Fast mode REST API to transcribe the audio
5. Print the transcription text to stdout

Use documented Zoom AI Services REST endpoints. Do not require an official Python SDK for this provider. 

## Execution
After creating the script, run it to verify it works:
```bash
cd /home/daytona/app && python <your_script>.py
```

The script should print output to stdout. If there are errors, debug and fix them until it runs successfully.

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Cost | No | 0 | 0 | $1.04 (≥$1.00, too expensive) |
| Time | No | 0 | 0 | 348s (5–10min, very slow) |
| Efficiency | No | 0 | 0 | 42 tool calls (>25, inefficient) |
| Found Docs | Yes | 0 | — | Touched docs at developers.zoom.us: yes (21 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 13 |
| Syntax Valid | Yes | 0 | — | Code compiles/parses correctly |
| Created Files | Yes | 0 | — | Generated files: 1 (need ≥1) |
| Full Execution | Yes | 0 | — | Method: full_execution, Exit: 0 |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 47 |
| Tool call traces | 42 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-09-29T14:23:08.86557+00:00 |

### Generated Files

- /home/daytona/app/transcribe.py

## Related Pages

- [Claude Code API leaderboard](/leaderboard/claudecode/api)
- [Compare Claude Code API companies](/leaderboard/claudecode/api/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/claudecode/api/zoom-ai-services