SiteCheck Agent Intel & Dev

Agent Intel Speech To Text Transcribe Turbo

agent_intel_speech_to_text_transcribe_turbo

Read-only

Transcribes an audio file (a public https URL or base64, up to 6 MB; WAV, MP3, M4A or OGG as the model accepts them) to text with a Cloudflare Workers AI Whisper model, returning the text and any timestamped segments the model gives. Requires the env.AI binding. Price: $0.004 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`audioUrl`	No	Public https URL of the audio file (WAV, MP3, M4A or OGG), up to 6 MB
`audioBase64`	No	Or the audio itself: base64 data (no data: prefix), up to 6 MB decoded

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 23, 2026

changedInput schema / properties / audioBase64 / description

Previous value: -"Base64 audio data (no data: prefix), up to 6 MB decoded"New value: +"Or the audio itself: base64 data (no data: prefix), up to 6 MB decoded"

addedInput schema / properties / audioUrl

Added value: +{
+  "description": "Public https URL of the audio file (WAV, MP3, M4A or OGG), up to 6 MB",
+  "type": "string"
+}

removedInput schema / required
```
Removed value: -[
-  "audioBase64"
-]
```

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses key behavior: it returns text plus timestamped segments, requires env.AI, costs $0.004 USDC per successful call via x402 on Base/Solana/Arc, and does not charge failed calls. This is substantial operational context for a paid, network-facing transcription tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core action and stays to two dense sentences. The remaining details about inputs, model, binding, payment, and failure charging all earn their place for a paid transcription tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists, the description need not explain return values, and it still summarizes them well. It covers formats, size, binding, pricing, and failure behavior, but does not explicitly resolve the fact that neither audio parameter is marked required in the schema, leaving the exactly-one-input expectation implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema already documents audioUrl and audioBase64 with format and size constraints. The description reinforces the URL-or-base64 input choice and size limit but does not add syntax, exclusivity, or validation semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: transcribes an audio file to text using a named Cloudflare Workers AI Whisper model. It also states the return shape (text and timestamped segments), making the tool clearly distinguishable from text-to-speech, OCR, and other siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context: the audio can be a public HTTPS URL or base64, with supported formats and a 6 MB limit, and requires the env.AI binding. It does not explicitly name when-not-to-use cases or direct agents to an alternative sibling, so it falls short of the top score.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SiteCheck Agent Intel & Dev tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?