# AssemblyAI Claude Code API Evaluation

**Category:** Voice STT
**Score:** 86 (B)

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

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 86 |
| Grade | B |
| Eval score | 81 |
| Discovery score | 100 |
| Cost | $0.18 |
| Runtime | 1m 20s |
| Tool calls | 9 |
| Errors | 1 |
| Tokens used | 238001 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | https://context7.com/assemblyai |
| llms.txt | https://www.assemblyai.com/docs/llms.txt |
| MCP server | https://www.assemblyai.com/docs/coding-agent-prompts |
| Typed SDK | https://github.com/AssemblyAI/assemblyai-node-sdk |
| OpenAPI | https://assemblyai.com/openapi.json |
| Agent skills | https://github.com/AssemblyAI/assemblyai-skill |
| CLI | https://github.com/AssemblyAI/cli |

## Evaluation Prompt

````text

# Task
Using https://www.assemblyai.com/docs, complete the following task:

Using the AssemblyAI Python SDK, build me a script that transcribes a sample audio file:

1. Install the official AssemblyAI Python SDK (pip install)
2. Transcribe this audio file and print the transcribed text:
   https://storage.googleapis.com/aai-web-samples/5_common_sports_injuries.mp3
3. If the SDK expects a local file, download the audio first
4. Print the transcription to stdout

You MUST use the official AssemblyAI Python SDK — do not make raw HTTP/REST calls. 

## 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 | Yes | 0 | 1 | $0.18 ($0.10–0.20, great) |
| Time | Yes | 0 | 1 | 80s (1–2min, great) |
| Efficiency | Yes | 0 | 1 | 9 tool calls (≤10, great) |
| Found Docs | Yes | 0 | — | Touched docs at assemblyai.com: yes (3 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 1 |
| 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 | 12 |
| Tool call traces | 9 |
| Generated files | 1 |
| Exit code | 0 |
| Completed at | 2026-09-23T04:10:43.767879+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/assemblyai