Convert audio or video from a URL into text with speaker labels and timestamps. Enable diarization to identify who said what in recordings.
Transcribe audio with speaker diarization and timestamps. Cost: 3 credits.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Language code. | en |
| audio_url | Yes | URL to audio/video file. | |
| speaker_labels | No | Enable speaker diarization. |
Changes observed during successful MCP inspections.
v0.3.1Input schema / properties / audio_url / descriptionPrevious value: -"URL to audio or video file"New value: +"URL to audio/video file."Input schema / properties / languageAdded value: +{
+ "default": "en",
+ "description": "Language code.",
+ "type": "string"
+}Input schema / properties / speaker_labels / descriptionPrevious value: -"Enable speaker diarization"New value: +"Enable speaker diarization."v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose a real behavioral trait: a cost of 3 credits, which lets the agent weigh expense. Beyond that it is silent on auth needs, file-size/duration limits, sync vs. async execution, and what the transcript output looks like.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, capability first and cost last, with no filler or repetition of the tool name. It is efficiently sized, though the brevity is closer to under-specification than to a fully earned five.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 3-parameter tool with a fully described schema and no output schema, the core is covered, but an agent still lacks the output shape (text? segments with speaker/time?) and cannot tell this apart from 'stt'. With no annotations to fall back on, those gaps matter more.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all three parameters are already documented in the schema, which sets the baseline at 3. The description's mention of diarization loosely maps to speaker_labels but adds no syntax, format, or default semantics beyond what the schema states.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb (Transcribe) and resource (audio) plus two differentiating features (speaker diarization, timestamps), so the agent knows what it produces. It does not, however, distinguish itself from the sibling 'stt' tool, which plausibly overlaps.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no when-to-use or when-not-to-use guidance, no prerequisites (e.g. URL must be publicly reachable), and no mention of the near-identical sibling 'stt' that an agent would need to choose against. The only implicit context is that this handles audio.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.