Botverse

Transcribe Uploaded Media

transcribe_media

Transcribe an already-uploaded video/audio file (from get_upload_url) into a speaker-labelled transcript. Same one-call pipeline and options as transcribe_from_url (attendee naming, srt/vtt, formatted docx/pdf). Use for local files or files larger than a URL fetch allows (up to 2 GB). CONSENT: you must have all parties' consent. Poll get_job_status (live stage) until complete, then get_download_url / get_output_content. ~$3 per hour of audio. RELIABILITY & FALLBACK: Botverse returns structured errors with a message. A bare 'HTTP 500' or 'tool call failed' with no message body is the MCP connector / sandbox layer between your client and Botverse — NOT a Botverse outage (the service is up if get_wallet_balance succeeds). If MCP calls keep failing, do NOT write your own ffmpeg / transcription / document-conversion code as a workaround — that wastes tokens and reinvents what Botverse does. Instead, tell the user to run the equivalent Botverse CLI from their own (non-sandboxed) machine, e.g. npx botverse transcribe <file> --to docx (also transcode and convert), then retry the MCP call.

Input Schema

TableJSON Schema

Name	Required	Description
`options`	No	Same options object as transcribe_from_url (attendees, language, diarize, max_speakers, title, include_timestamps, also_deliver).
`object_key`	Yes	The object_key returned by get_upload_url.
`output_format`	Yes	Primary deliverable: txt \| json \| srt \| vtt \| docx \| pdf

Output Schema

TableJSON Schema

Name	Required	Description
`job_id`	Yes	Unique identifier for this job. Pass to get_job_status and get_download_url.
`status`	Yes	Initial job state — always queued or processing immediately after submission.
`estimated_seconds`	No	Rough estimated processing time in seconds. Actual time may vary.

TDQS

A4.6/5.0

Behavior5/5

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

Despite annotations lacking depth, the description discloses critical behavioral traits: async job lifecycle with polling, cost per hour of audio, consent requirements, and a detailed reliability section explaining that bare HTTP 500s may come from the MCP connector layer, not Botverse. It even warns against writing custom workaround code. This goes far beyond annotation hints.

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?

The description is long but well-structured with clear section labels (CONSENT, RELIABILITY & FALLBACK). Every sentence carries operational value, and purpose is front-loaded. However, the reliability/fallback content is quite dense and could be seen as slightly over-explained for a tool definition, keeping it at 4 rather than 5.

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?

For a complex async tool, the description is remarkably complete: it covers prerequisites (upload via get_upload_url), usage boundaries, consent, follow-up workflows (poll status, download), cost, error interpretation, and fallback CLI instructions. Combined with an output schema, the agent has all context needed to invoke correctly.

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 coverage is 100% with meaningful descriptions for all three parameters (object_key, output_format, options). The schema already mentions 'Same options object as transcribe_from_url' and 'The object_key returned by get_upload_url', so the description adds no new parameter-level meaning. Baseline 3 applies.

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?

Purpose is explicit and specific: transcribe an already-uploaded video/audio file (from get_upload_url) into a speaker-labelled transcript. It clearly distinguishes from sibling `transcribe_from_url` by focusing on uploaded objects and larger files, and even names the source workflow.

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

Usage Guidelines5/5

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

The description explicitly states when to use this tool (local files or files > URL fetch limit, up to 2 GB) and references the sibling `transcribe_from_url` for URL-based cases. It also gives a full workflow (poll `get_job_status`, then retrieve) plus fallback guidance and cost/consent notes, leaving no ambiguity about usage.

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

All Botverse tools Inspect

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

A4/5.0

Disambiguation4/5

Tools are largely distinguishable by their action and input source (content/file/url), but the multiple convert_* and transcode/transcribe variants overlap in purpose, and get_job_status vs get_workflow_status could cause confusion. Descriptions are thorough enough to guide selection, but the boundaries between similar actions are not always crisp.

Naming Consistency4/5

All names use snake_case with a verb-noun pattern (get_, convert_, transcode_, transcribe_, submit_, cancel_), which is consistent. However, the variant naming is not perfectly parallel: convert_content/file/from_url use a source suffix, whereas transcode_video vs transcode_from_url and transcribe_media vs transcribe_from_url mix output type and source, creating minor inconsistency.

Tool Count4/5

At 15 tools, the server is at the upper end of a well-scoped set. Each tool supports a distinct input/output route or workflow function, but the count is slightly heavy due to multiple variants of similar operations. It remains appropriate for the breadth of conversion, transcoding, transcription, workflow, and wallet features.

Completeness3/5

The core job lifecycle (submit, poll, retrieve output) is well covered, and workflows have submit/status/cancel. However, get_upload_url references a transcode_content tool that does not exist in the toolset, and there is no way to cancel a single job (only full workflows). This leaves gaps for inline media transcoding in sandboxed environments and granular job control.

Resources

Need Help?