# SuanLinFang AI Capabilities

> SuanLinFang AI Capabilities is a paid MCP server for files and documents. MCP endpoint for pay-as-you-go speech-to-text, text-to-speech, OCR and decision APIs. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** Web, API
- **Website:** https://suanlinfang.cn
- **MCP Registry name:** cn.suanlinfang/stt-tts-ocr-decision
- **Categories:** files and documents, design and media, AI models and LLM tooling
- **Listing updated:** 2026-11-14

## About

SuanLinFang (算邻坊) is a Chinese-language platform that runs AI services on a shared pool of idle GPUs. Its MCP endpoint fronts four capabilities: speech recognition, speech synthesis, text recognition (OCR) and what it calls typed decision-making.

The site publishes per-use prices: speech recognition at 0.5 yuan per hour, speech synthesis at 2 yuan per 10,000 characters, OCR at 0.5 fen per page and decision-making at 2 yuan per million tokens. New users get a 10 yuan trial credit, and you pay nothing when you do not use it. The REST API uses a Bearer key and JSON bodies in a style the site says matches major model vendors, with long audio, long text and PDFs handled as asynchronous jobs.

There are also no-code online tools, an AI translation product built on the same network, and a client download for people who want to contribute GPU capacity and earn income, withdrawable via WeChat from 1 yuan.

## Features

- **Speech recognition:** Transcribes audio, priced per hour of audio.
- **Speech synthesis:** Converts text to audio, priced per 10,000 characters.
- **Text recognition:** OCR for images and PDFs, priced per page.
- **Decision-making API:** Typed decision outputs billed per million tokens.
- **Async jobs:** Long audio, long text and PDFs run as asynchronous tasks.
- **No-code tools:** Online tools let you try the capabilities without writing code.

## Good for

- Transcribe recordings or meetings
- Generate speech from text
- Extract text from scanned pages
- Call a decision API from an agent
- Test capabilities with the 10 yuan starter credit

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http stt-tts-ocr-decision https://suanlinfang.cn/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://suanlinfang.cn/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "stt-tts-ocr-decision": {
      "url": "https://suanlinfang.cn/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "stt-tts-ocr-decision": {
      "type": "http",
      "url": "https://suanlinfang.cn/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "stt-tts-ocr-decision": {
      "serverUrl": "https://suanlinfang.cn/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "stt-tts-ocr-decision": {
      "type": "http",
      "url": "https://suanlinfang.cn/mcp"
    }
  }
}
```

## Tools

- `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。
- `submit_transcription_task`: 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。
- `get_transcription_task`: 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。
- `synthesize_speech`: 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。
- `submit_speech_task`: 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。
- `get_speech_task`: 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。
- `list_tts_voices`: 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。
- `recognize_image`: 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）。
- `submit_document_task`: 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。
- `get_document_task`: 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。
- `decide`: 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","criter

## FAQ

### How is it priced?

Pay as you go: 0.5 yuan per hour for speech recognition, 2 yuan per 10,000 characters for synthesis, 0.5 fen per OCR page and 2 yuan per million tokens for decisions.

### Is there a free trial?

New users receive 10 yuan of trial credit.

### How do I authenticate?

The API uses a Bearer key and JSON request bodies.

### Where is the MCP endpoint?

https://suanlinfang.cn/mcp over streamable HTTP.

### Is SuanLinFang AI Capabilities free?

No. SuanLinFang AI Capabilities is a paid product.

### How do I add SuanLinFang AI Capabilities to Claude Code?

Run this command in your terminal: claude mcp add --transport http stt-tts-ocr-decision https://suanlinfang.cn/mcp

### What are the best alternatives to SuanLinFang AI Capabilities?

The closest alternatives to SuanLinFang AI Capabilities are HyperFrames by HeyGen, ffmpeg-skill, Claude Code Ultimate Guide, ASTra and AvatarSay — Fictional Character & Talking Video MCP.

## Alternatives

- [HyperFrames by HeyGen](https://ai-powered.com/mcp/hyperframes-by-heygen): HyperFrames by HeyGen is a freemium MCP server for design and media.
- [ffmpeg-skill](https://ai-powered.com/mcp/ffmpeg-skill): ffmpeg-skill is an open-source MCP server for design and media.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [ASTra](https://ai-powered.com/mcp/astra): ASTra is a freemium MCP server for files and documents.
- [AvatarSay — Fictional Character & Talking Video MCP](https://ai-powered.com/mcp/avatarsay-fictional-character-and-talking-video-mcp): AvatarSay — Fictional Character & Talking Video MCP is a freemium MCP server for design and media.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.
- [VfxSmith](https://ai-powered.com/mcp/vfxsmith): VfxSmith is a freemium MCP server for design and media.
- [CalderFlow](https://ai-powered.com/mcp/calderflow): CalderFlow is a free MCP server for design and media.

---
Source: https://ai-powered.com/mcp/suanlinfang-ai-capabilities
