Scoutari

AI builder 的決策情報台。

瀏覽

  • 今日情報
  • Skill 榜單
  • AI 週報
  • 關於與編輯方針
  • RSS

主題

  • 模型發布
  • API 與價格
  • MCP 與 Skills
  • AI Coding
  • 中國模型
  • 開源模型
  • Agent
  • Infra / 成本
  • 值得試用
© 2026 Scoutari · scoutari.com摘要由 AI 輔助生成，並始終附上原文連結。
情報收藏週報設定
SScoutariAI Builder Intel · decision desk
Skill RadarSavedPersonalizeSubmit sourceLog inSign up
Sign up
Skill RadarSavedPersonalizeSubmit sourceLog in
Back to timeline

Mon, July 609:45Open SourceModel releasesAPI & pricingOpen source

FunASR Industrial Speech Recognition Toolkit: 170x Real-Time, 50+ Languages, Speaker Diarization & Emotion Detection

View original

Decision Brief

What changedFunASR is an industrial-grade open-source speech recognition toolkit supporting 170x real-time factor, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
Why it mattersFor developers needing efficient speech recognition, 170x real-time factor plus emotion detection and streaming greatly expand real-time voice application deployment.
Who should careOpen-source model users
Affected stackOpenAI
Source confidenceHigh · Official release / blog / repo

Developed by ModelScope, FunASR has 18,912 stars on GitHub (+248 in 7 days). Key highlights: 170x real-time factor (processing 1 second of audio in about 6 ms), 50+ languages, built-in speaker diarization and emotion detection, streaming capability, and an OpenAI-compatible API. For developers using speech recognition (e.g., customer service systems, meeting transcription, real-time translation), FunASR offers a deployable industrial-grade solution without training models from scratch. Emotion detection can be applied to sentiment analysis, and the OpenAI-compatible API allows seamless migration for existing OpenAI speech service users. As open source, it is also suitable for customization or integration into existing pipelines.

Summary basis: official / RSS sourceCompiled from the source scope noted above; the original remains authoritative.

Sources

  • Skill Radar（GitHub 趨勢）

    Trending hands-on MCP servers, agent skills, and AI-coding tools discovered from GitHub search momentum.

  • GitHub：modelscope/FunASR

Related intel

  • liyupi/ai-guide: AI Resource Collection and Vibe Coding Tutorial Hits GitHub Trending

    liyupi/ai-guide, an open-source project on AI resources and Vibe Coding tutorials, hits GitHub trending.

  • LibreChat: Enhanced ChatGPT Clone with Multi-Model, Agent & MCP Support

    LibreChat is an open-source, self-hosted enhanced ChatGPT clone supporting Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, and more.

  • DeusData/codebase-memory-mcp: High-Performance Code Intelligence MCP Server Indexes Codebase as Persistent Knowledge Graph

    High-performance MCP server indexing codebases into persistent knowledge graphs with millisecond processing for average repos.

  • ECC Launches Agent Performance Optimization Framework for Claude Code, Codex, Cursor, etc.

    GitHub trending project ECC launches as an agent performance optimization system, offering skills, instincts, memory, and security.