Skip to main content
Glama

transcribe_from_url

Download video from a URL and generate accurate subtitles using Whisper speech recognition. Supports language detection, translation, and customization for precise transcription results.

Instructions

URLから動画をダウンロードして字幕を生成します。

Args:
    url: 動画のURL(YouTube等)
    device: 推論に使用するデバイス ("cuda" または "cpu")
    model_size: Whisperモデルサイズ (デフォルト: "large-v3")
    input_lang: 入力言語コード(省略時は自動検知)
    output_lang: 翻訳先言語コード(省略時は翻訳なし)
    initial_prompt: 専門用語や固有名詞のヒントを提供するプロンプト
    condition_on_previous_text: 前のセグメントを参照して文脈維持 (デフォルト: False、ハルシネーション防止)
    temperature: 温度パラメータ(0.0で最も決定的、デフォルト: 0.0)
    no_speech_threshold: 無音判定の閾値 (デフォルト: 0.6)
    compression_ratio_threshold: 繰り返し検出の閾値 (デフォルト: 2.4)
    vad_filter: 音声区間検出フィルタを使用 (デフォルト: True、ハルシネーション防止)

Returns:
    生成されたSRTファイルのパスと検出された言語情報

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes
deviceNocuda
model_sizeNolarge-v3
input_langNo
output_langNo
initial_promptNo
condition_on_previous_textNo
temperatureNo
no_speech_thresholdNo
compression_ratio_thresholdNo
vad_filterNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNo
successYes
srt_pathNo
segment_countNo
detected_languageNo
translated_srt_pathNo
Behavior4/5

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

With no annotations provided, the description carries full burden and does well by explaining key behaviors: downloading videos, generating subtitles, language detection/translation capabilities, hallucination prevention mechanisms, and return values. It mentions 'ハルシネーション防止' (hallucination prevention) for two parameters, which is valuable behavioral context not evident from schema alone.

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 well-structured with clear sections (Args, Returns) and each parameter explanation is concise yet informative. While comprehensive, it maintains efficiency - every sentence serves a purpose in explaining the tool's functionality or parameters. Minor deduction because the purpose statement could be slightly more front-loaded.

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?

Given the tool's complexity (11 parameters, video processing), no annotations, but with output schema present, the description provides excellent completeness. It explains the core functionality, all parameters with semantics, behavioral traits like hallucination prevention, and mentions return values. The output schema handles return format details, so the description appropriately focuses on usage context.

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

Parameters5/5

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

With 0% schema description coverage, the description fully compensates by providing clear semantic explanations for all 11 parameters. Each parameter gets a meaningful description in Japanese that explains its purpose, defaults, and practical implications (e.g., '専門用語や固有名詞のヒント' for initial_prompt, 'ハルシネーション防止' for condition_on_previous_text). This adds substantial value beyond the bare schema.

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 clearly states the tool's purpose: 'URLから動画をダウンロードして字幕を生成します' (downloads video from URL and generates subtitles). It specifies the verb (download and generate), resource (video from URL), and distinguishes from sibling 'transcribe_from_file' by specifying URL input rather than file input.

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

Usage Guidelines3/5

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

The description implies usage context through parameter explanations (e.g., 'YouTube等' suggests video platforms), but doesn't explicitly state when to use this tool versus 'transcribe_from_file' or 'get_supported_languages'. It provides technical context but lacks explicit guidance on tool selection scenarios.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/uzusio/faster-whisper-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server