Skip to main content
Glama

transcription

by com.scriptivox.www

transcribe_url

Transcribe audio or video from a public URL using Scriptivox AI. Supports 119 languages, speaker diarization, and word-level timestamps. RECOMMENDED: always pass the language parameter explicitly when you know the audio language — auto-detect has a small failure rate on short clips, code-switched audio, or files starting with music. Requires a configured API key.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesPublic URL to an audio or video file (http/https). Supports Google Drive, Dropbox, OneDrive sharing links, and direct file URLs.
alignNoWord-level timestamps + confidence scores. Default: true. Pass false to opt out (ignored when diarize: true).
diarizeNoEnable speaker diarization. Default: false. When true, word-level alignment is automatically enabled regardless of `align`.
languageNoISO 639-1 language code (e.g. "en", "es", "fr"). 119 languages supported. Strongly recommended when you know the language.
webhook_urlNoOptional HTTPS URL where transcription.* events will be POSTed (HMAC-signed).
speaker_countNoExpected number of speakers (1-50). Requires diarize: true. Passing this when known improves diarization accuracy.
await_completedNoDefault: true. When false, return the transcription_id immediately without polling.
idempotency_keyNoOptional Idempotency-Key header (up to 255 chars). Same key + same body = same transcription_id.

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already mark readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false; the description adds beyond these by disclosing an auth requirement ('Requires a configured API key') and a known failure mode of auto-detection. It does not contradict annotations, and the added context helps agents anticipate edge cases even though side effects like cost are not mentioned.

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?

Four sentences, each earning its place: purpose, capabilities, parameter recommendation with rationale, and prerequisite. The recommendation is front-loaded in a clearly highlighted RECOMMENDED block, and there is no filler or repetition of schema content.

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

Completeness3/5

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

The description conveys the core operation and a key usage caveat, but with no output schema it omits the return value and the async/polling behavior implied by await_completed and webhook_url. It also does not mention that transcription can be long-running or that webhook events will be delivered. This leaves an agent partially uninformed about what to expect after calling the 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%, establishing a baseline of 3. The description adds value beyond the schema by recommending the language parameter explicitly and explaining the failure conditions that justify it. It also ties top-level features (diarization, word-level timestamps) to the relevant parameters, giving agents extra semantic anchoring.

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 opens with a specific verb and resource: 'Transcribe audio or video from a public URL using Scriptivox AI.' This clearly distinguishes it from sibling transcribe_upload (local file upload) and transcription_url (URL retrieval) by emphasizing the public-URL input. The feature summary (119 languages, diarization, timestamps) reinforces scope.

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?

The description gives concrete guidance on when to pass the language parameter explicitly, noting auto-detect failure on short clips, code-switched audio, and music-leading files. It also states the API key requirement. It does not explicitly contrast with alternatives (e.g., when to prefer transcribe_upload), but the public-URL wording and parameter guidance supply clear usable context.

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

All transcription toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation3/5

The set contains several near-neighbor groups: deprecated aliases duplicate live tools, and docs/billing/financial tools have fuzzy boundaries. Individual descriptions are detailed and resolve most collisions, but matching the right tool among 39 still requires care.

Naming Consistency3/5

Most tools follow a sensible verb_object style, but the transcribe_* group is inconsistent: transcribe_url/transcribe_upload are verb_object, while transcribe_status/transcribe_cancel/transcribe_delete are really status/cancel/delete operations renamed with a transcribe prefix. The deprecated transcription_status/transcription_url aliases add another naming convention, so the pattern is not reliable across the set.

Tool Count2/5

39 tools is well over the 25+ threshold and creates an overwhelmingly broad surface spanning account management, billing, docs, API jobs, library organization, meeting bots, and automations. Two deprecated duplicates inflate the count further. This would be more coherent split into separate servers or at least pruned of deprecated aliases.

Completeness3/5

Core API transcription lifecycle is covered, and the library/meeting-bot flows have search, tagging, moving, and audio retrieval. However, there is no user-library deletion/rename, no OAuth-side full-transcript access, local upload is non-functional over the hosted endpoint, and webhook management is documented but not exposed as tools. These gaps force agents to work around missing operations.

Resources