# Speechify Codex API Evaluation

**Category:** Voice TTS
**Score:** 75 (B)

This is the agent-readable Devtool Arena evaluation page for Speechify on Codex API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 75 |
| Grade | B |
| Eval score | 83 |
| Discovery score | 57 |
| Cost | $0.15 |
| Runtime | 48s |
| Tool calls | 19 |
| Errors | 2 |
| Tokens used | 451079 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | https://docs.speechify.ai/llms.txt |
| MCP server | https://docs.speechify.ai/build/guides/get-started/connect-mcp |
| Typed SDK | https://docs.speechify.ai/build/guides/get-started/official-sdks |
| OpenAPI | https://docs.speechify.ai/openapi.json |
| Agent skills | Not found |
| CLI | Not found |

## Evaluation Prompt

````text

# Task
Using https://docs.speechify.ai/tts/api-reference/introduction, complete the following task:

Using Speechify, build me a Python script that converts text to speech:

1. Follow the Speechify documentation to authenticate and choose the simplest text-to-speech API path
2. Convert this text to speech:
   "Your order has been shipped and will arrive by Friday."
3. Save the audio as output.mp3. If only WAV output is supported, save it as output.wav instead
4. Print a confirmation message with the filename when the file is saved

Use documented Speechify APIs only; do not generate fake or placeholder audio. 

## 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 | $0.15 ($0.10–0.20, great) |
| Time | Yes | 0 | 1 | 48s (<60s, excellent) |
| Efficiency | Yes | 0 | 0 | 19 tool calls (≤20, acceptable) |
| Found Docs | Yes | 0 | — | Touched docs at docs.speechify.ai: yes (12 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 2 |
| Syntax Valid | Yes | 0 | — | Code compiles/parses correctly |
| Created Files | Yes | 0 | — | Generated files: 2 (need ≥1) |
| Full Execution | Yes | 0 | — | Method: full_execution, Exit: 0 |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 23 |
| Tool call traces | 19 |
| Generated files | 2 |
| Exit code | 0 |
| Completed at | 2026-09-27T01:58:07.423225+00:00 |

### Generated Files

- /home/daytona/app/requirements.txt
- /home/daytona/app/generate_speech.py

## Related Pages

- [Codex API leaderboard](/leaderboard/codex/api)
- [Compare Codex API companies](/leaderboard/codex/api/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/codex/api/speechify