Skip to main content
Glama

SuanLinFang AI Capabilities

Server Details

Speech-to-text, text-to-speech, OCR and typed decision-making APIs from suanlinfang.cn.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.9/5.0

Scored across 11 tools

Disambiguation4/5

Each tool maps to a distinct modality+mode (image OCR vs PDF OCR, short sync TTS vs long async TTS, short sync ASR vs long async ASR, plus a standalone decision tool), and descriptions explicitly cross-reference the async alternatives so an agent can pick correctly. The only residual risk is at-a-glance confusion between sync/async sibling pairs (synthesize_speech vs submit_speech_task, transcribe_audio vs submit_transcription_task), which the text resolves but the names alone do not.

Naming Consistency4/5

Strong verb_noun pattern throughout (get_*_task, submit_*_task, list_tts_voices, recognize_image, synthesize_speech, transcribe_audio), and submit_X_task correctly pairs with get_X_task for polling. The lone deviation is 'decide', a bare verb with no noun, which breaks the otherwise uniform scheme.

Tool Count5/5

Eleven tools is well within the sweet spot and every one earns its place: three async submit/poll pairs, three sync operations, a voice-list helper, and one judgment tool. No redundant or filler tools.

Completeness4/5

The surface covers the full sync/async lifecycle for OCR, TTS, and ASR, including task status polling and voice discovery. Minor gaps remain: no task cancellation or task listing, no timestamped/diarized transcription output, and no coverage for adjacent capabilities like image generation or translation that 'AI Capabilities' might imply.

Available Tools

11 tools
decideDecideAInspect

智能决策(System One 类型化判断):输入业务状态与若干类型化问题,返回每题的校准概率,不生成文本。 适用:工单分类、风控判定、质检评估等结构化判断场景。无上下文记忆,每次请求独立。 questions 为 {题目id: 题目} 映射(1-32 题),type 三种:choice(多选一,criteria={选项名:描述})、 noul(是否判断,criteria 可选 {true:描述,false:描述})、score(有序等级打分,criteria=[等级描述...]),可选 instructions 说明该问什么。 示例:{"team":{"type":"choice","criteria":{"refund":"退款","logistics":"物流"}},"urgent":{"type":"noul"},"severity":{"type":"score","criteria":["轻微","一般","严重"]}} answers 按同键回传,含选中项、置信度与全选项概率。 计费按输入 token(约 2 元/百万,输出免费),失败不计费。

Inputs: state (required), questions (required). Returns: object

get_document_taskGet Document TaskAInspect

查询 PDF 文档识别任务状态。status:queued/running(看 doneUnits/totalUnits 进度)、 success(resultUrl 为聚合结果下载链接)、failed(errorMsg)。任务终态保留 72 小时。

Inputs: task_no (required). Returns: object

get_speech_taskGet Speech TaskAInspect

查询长文本语音合成任务状态。status:queued/running(看 doneUnits/totalUnits)、 success(resultUrl 为完整音频下载链接,1 小时内有效,过期重查即换新链)、failed(errorMsg)。 任务终态保留 72 小时。

Inputs: task_no (required). Returns: object

get_transcription_taskGet Transcription TaskBInspect

查询长音频转写任务状态。status:queued/running(进行中,看 doneUnits/totalUnits 进度)、 success(text 为全文转写)、failed(errorMsg 为失败原因)。任务终态保留 72 小时。

Inputs: task_no (required). Returns: object

list_tts_voicesList Tts VoicesAInspect

查询语音合成当前可用音色清单(code/name/gender/styleTag)。合成前先看这个选 speaker。

Inputs: no named parameters. Returns: result

recognize_imageRecognize ImageAInspect

识别图片中的文字(png/jpg/webp/bmp,≤20MB,公网 URL),同步返回逐行文本。 tier:standard 标准档(快速,适合清晰打印件/截图);accurate 精准档(表格、多栏、倾斜拍摄等复杂版面)。 prompt 仅精准档生效:自定义识别指令(如「只提取表格金额列」),≤2000 字符,缺省识别全部文字。 计费按页(单图=1 页,约 0.5~1.5 分/页)。

Inputs: tier (required), image_url (required), prompt. Returns: object

submit_document_taskSubmit Document TaskAInspect

提交 PDF 文档识别任务(≤200MB、≤500 页,逐页识别整本)。适合扫描合同/书籍/报告。 提交后用 get_document_task 轮询结果。prompt 仅精准档生效。计费按页。

Inputs: tier (required), document_url (required), prompt, file_name. Returns: object

submit_speech_taskSubmit Speech TaskAInspect

提交长文本语音合成任务(≤20 万字):平台按 500 字切块合成并拼接为完整音频。 提交后用 get_speech_task 轮询结果。计费约 2 元/万字符。

Inputs: text (required), speaker, audio_format. Returns: object

submit_transcription_taskSubmit Transcription TaskAInspect

提交长音频转写任务(会议录音/播客/网课,最长 2 小时、≤500MB,wav/mp3/flac/m4a/ogg/aac)。 平台自动按 180 秒切段逐段转写并拼接全文(纯文本,不含时间戳)。提交后用 get_transcription_task 轮询结果。 language 留空自动检测,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),对全部音频段生效。 计费按实际时长(约 0.5 元/小时),余额不足会在提交时被拒绝。

Inputs: audio_url (required), context, language, file_name. Returns: object

synthesize_speechSynthesize SpeechAInspect

把文本合成为语音(≤3000 UTF-8 字节,约 1000 汉字),同步返回现签下载链接(url,GET 即得音频,1 小时内有效)。 请提醒用户及时下载转存——链接过期后只能重新合成(重复计费)。 更长的文本请改用 submit_speech_task(异步任务)。speaker 音色代码先用 list_tts_voices 查询。 计费约 2 元/万字符,失败不计费。

Inputs: text (required), speaker, audio_format. Returns: object

transcribe_audioTranscribe AudioAInspect

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。

Inputs: audio_url (required), context, language. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A powerful speech-to-text MCP server that supports multiple audio formats and recognition engines including remote APIs (Bailian, OpenAI Whisper, iFLYTEK), Google Speech Recognition, and CMU Sphinx.
      1
      -
    • A
      license
      A
      quality
      C
      maintenance
      Provides on-device Chinese speech recognition with traditional Chinese (Taiwan) output via MCP server, HTTP API, and CLI, ensuring privacy by processing audio locally without uploading to cloud services.
      2
      1
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources