SuanLinFang — STT / TTS / OCR / Decision APIs

Transcribe Audio

transcribe_audio

把一段短音频（公网 URL）转成文字。适用于 ≤3 分钟、≤20MB 的录音/语音消息，同步秒级返回。更长的音频请改用 submit_transcription_task（异步任务）。 language 留空自动检测（支持普通话、英语及 22 种中文方言）；指定时用语种代码（如 zh、en）。 context 可传热词（人名、术语、品牌，逗号分隔），专有名词按所列写法优先转写——会议转写建议填与会人名。返回全文纯文本（不含时间戳/分句时间轴）。计费按音频实际时长（约 0.5 元/小时，精确到秒），失败不计费。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "audio_url": "<audio_url>"
    },
    "name": "transcribe_audio"
  }
}

Input Schema

Name	Required	Description	Default
`context`	No
`language`	No
`audio_url`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.7/5.0

Behavior4/5

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

With no annotations at all, the description carries the full burden and mostly meets it, disclosing synchronous seconds-level latency, plain-text-only output (no timestamps/segmentation), per-second billing at ~0.5 yuan/hour, and that failed calls are not billed. Authentication, rate limits, and concurrency behavior are not mentioned, which keeps it short of a 5.

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?

Every line does work: purpose and hard limits come first, then the routing alternative, then parameter behavior, then output and billing. There is no repetition of the schema and no padding.

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?

Although an output schema exists, the description still states the return is plain text without timestamps, and it covers the cost model, latency, limits, and the async alternative. Nothing an agent needs in order to decide and invoke correctly is missing; only auth/rate-limit details are absent, and those are typically handled by the harness.

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 0%, so the description has to explain all three parameters, and it does: the audio_url must be a publicly reachable short audio file subject to the size and duration limits, language left empty triggers auto-detection (Mandarin, English, 22 Chinese dialects) while a code such as zh/en forces it, and context accepts comma-separated hot words that prioritize the listed proper nouns. That is well beyond the bare schema, though audio_url format details and the exact effect of mixing hot words with auto-detected languages stay implicit.

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 gives a specific verb and resource ("把一段短音频...转成文字") and scopes it to <=3 minutes / <=20MB public-URL audio with synchronous return. It also names the sibling tool (submit_transcription_task) that covers the opposite case, so the agent can tell the two apart without opening a schema.

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?

Both selection conditions are stated explicitly: use this for short recordings/voice messages under the size and duration limits, and switch to submit_transcription_task for longer audio (async). The agent cannot confuse which tool to use for long audio because the routing condition is spelled out.

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

All SuanLinFang — STT / TTS / OCR / Decision APIs tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?