switch

Transcribe Audio

transcribe_audio

Write out everything said in a recording, with the exact second every word starts and ends. Give it the asset id of a clip in your library (or an https link) and you get back the full text, the language it heard, and a word-by-word list with times you can build captions or cut on. Set speakers true when more than one person is talking and each word is also labelled with who said it. Set sound_events true to have laughter, applause and other noises marked too. Pass keyterms, a list of words or short phrases (up to 1000, each under 50 letters and 5 words or fewer), to make sure names, product words and acronyms come out spelled the way you write them, for example ["QA"] so it is not heard as "Q&A". Works on audio and on video files. Billed per minute of the recording (a charge applies). Nothing new is saved to your library.

Input Schema

Name	Required	Description
`keyterms`	No	Optional. Words or short phrases to hear right, spelled the way you want them back, e.g. ["QA", "SwitchApp"]. Up to 1000, each under 50 letters and 5 words or fewer, with no < > { } [ ] or backslash.
`language`	No	Optional two-letter language code, e.g. "en". Leave out and the language is worked out automatically.
`speakers`	No	Optional. true labels each word with who said it, for two or more people talking.
`recording`	Yes	The clip to write out: an asset id from your library, the generation_id any Switch audio tool gave back (list_my_audio shows them), or an https link.
`sound_events`	No	Optional. true marks non-speech sounds like laughter and applause.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 24, 2026

changedInput schema / properties / recording / description

Previous value: -"The clip to write out: an asset id from your library, or an https link."New value: +"The clip to write out: an asset id from your library, the generation_id any Switch audio tool gave back (list_my_audio shows them), or an https link."

Changed1 schema field changedOct 23, 2026

addedInput schema / properties / keyterms

Added value: +{
+  "description": "Optional. Words or short phrases to hear right, spelled the way you want them back, e.g. [\"QA\", \"SwitchApp\"]. Up to 1000, each under 50 letters and 5 words or fewer, with no < > { } [ ] or backslash.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

AddedOct 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Adds real behavioral context beyond the annotations: billing is per minute of recording ('a charge applies'), no new asset is persisted ('Nothing new is saved to your library'), and language is auto-detected when omitted. With readOnlyHint=false the billing/mutation nuance matters, and the description handles it without contradicting the annotations.

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

Conciseness4/5

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

Purpose and inputs come first, with billing and persistence constraints trailing as a useful caveat. It is dense and mostly earns its length, though the keyterms example (["QA"] vs "Q&A") duplicates what is already in the schema and could be trimmed.

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

Completeness5/5

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

There is no output schema, and the description compensates fully by describing the return shape — full text, detected language, and a word-by-word list with start/end times. Combined with billing and no-persistence notes, an agent has everything needed to call and interpret this tool.

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

Parameters4/5

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

Schema coverage is 100%, so a 3 is the baseline. The description still adds intent: keyterms exists so names and acronyms 'come out spelled the way you write them', and the timing list is framed as 'times you can build captions or cut on'. It does not cover the optional `language` parameter, keeping it just above baseline.

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?

States a specific verb and resource — 'Write out everything said in a recording' — plus the exact output (full text, detected language, word-level timings). This is clearly distinguishable from siblings like dub_audio, isolate_voice, or align_words without opening any schema.

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?

Gives actionable guidance for each optional flag: 'Set speakers true when more than one person is talking', 'Set sound_events true to have laughter, applause...', and explains the purpose of keyterms. It also states it works on audio and video. It stops short of naming sibling alternatives (e.g., dub_audio for translation, align_words for alignment), so exclusion guidance is absent.

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

All switch 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?