Skip to main content
Glama
danielrosehill

Gemini Transcription MCP

by danielrosehill
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

transcribe_audio_raw

Transcribe any audio file to an exact verbatim transcript, preserving filler words, false starts, and repetitions. Ideal when you need raw speech-to-text without any cleanup or editing.

Instructions

Transcribes an audio file using Gemini via OpenRouter. Returns a verbatim transcript with NO cleanup - preserves filler words, false starts, and repetitions exactly as spoken. Use this when you need exact speech-to-text without any editing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vadNoEnable Voice Activity Detection preprocessing. Strips silence and non-speech audio before transcription using Silero VAD. Useful for recordings with long pauses or background noise.
modelNoModel to use: "lite" for Gemini 3.1 Flash Lite (default, cost-efficient), "flash" for Gemini 3 Flash (more capable). Also accepts full OpenRouter model IDs.
file_urlNoHTTP(S) URL where the audio file can be fetched. PREFERRED transport for remote clients — use a presigned URL from `s3-stage <path>` on the workstation. Provide this OR file_content.
ssh_hostNoSSH host (and optional port, e.g. host:2222) to pull the audio file from. Provide with ssh_path.
ssh_pathNoRemote file path on the SSH host. Provide with ssh_host.
ssh_portNoOptional SSH port when pulling the file.
ssh_userNoOptional SSH username when pulling the file.
file_nameNoOptional name of the audio file, including the extension. Helpful when using URLs without a filename.
output_dirNoOptional directory path where the transcript will be saved as a markdown file. If provided, saves the transcript with a descriptive filename derived from the title.
file_contentNoBase64-encoded audio content. AVOID for anything beyond a few seconds of audio — base64 inlining of audio is large and unreliable. Prefer file_url with `s3-stage` for local workstation files. Provide this OR file_url.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.8.1

TDQS

A3.6/5.0
Behavior3/5

Does 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 key behavioral trait: the output is verbatim with no cleanup, preserving filler words, false starts, and repetitions. It also reveals the underlying model provider. However, it does not describe how the transcript is returned (e.g., text output vs. saved file), error behavior, or transport-related edge cases, leaving some behavioral ambiguity.

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 two sentences with zero filler. The primary function and the key 'no cleanup' differentiator are front-loaded, and the usage guidance is concise. Every sentence earns its place.

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

Completeness2/5

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

This is a complex tool with 10 parameters, multiple file transport options (file_url, ssh, file_content), and five sibling tools, yet the description gives no guidance on choosing between these transports or explaining the output format/saving behavior. The schema covers parameter syntax but not how to decide among the three mutually exclusive source options. For the tool's complexity, the description is under-specified.

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%, so the baseline is 3. The description itself adds no parameter-level meaning beyond the schema; it only mentions audio file generically. With all ten parameters already well-documented in the schema, this is acceptable, and the description neither compensates nor detracts.

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

Purpose4/5

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

The description clearly states the verb 'Transcribes', the resource (audio file), and the underlying provider (Gemini via OpenRouter). It also highlights the distinguishing output trait: a verbatim transcript with NO cleanup, preserving filler words and repetitions. However, it does not explicitly identify how this differs from sibling tools like transcribe_audio or transcribe_with_preset, leaving some differentiation to inference from the 'raw' name.

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 provides clear usage context: 'Use this when you need exact speech-to-text without any editing.' This tells the agent when to choose this tool. It does not discuss when NOT to use it or recommend alternatives, so it stops short of the full 5-level guidance.

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

Deploy Server

Other Tools