crispasr-agent-transcriber
Local-only transcription for Codex and MCP-based AI agents, powered by CrispASR. No cloud uploads, no API keys required for transcription.
GitHub Release | npm installer | |
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
uvx crispasr-agent-transcriber==0.4.0Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add io.github.emiyakatuz-crispasr-agent-transcriber -- uvx crispasr-agent-transcriber==0.4.0在終端機中執行。
{ "mcpServers": { "io.github.emiyakatuz-crispasr-agent-transcriber": { "command": "uvx", "args": [ "crispasr-agent-transcriber==0.4.0" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Local-only transcription for Codex and MCP-based AI agents, powered by CrispASR. No cloud uploads, no API keys required for transcription.
GitHub Release | npm installer | |
Transcribe and understand local audio/video with CrispASR and local models only.
Give it a local audio or video file. It:
/v1/audio/transcriptions endpoint.Everything runs on your machine. Media never leaves it.
The plugin includes the Codex Skill, command-line tool, and MCP server. Media
stays on your computer. Model files are never downloaded during install/update;
use the explicit models command when you want the installer to fetch them.
node --version
uv --version
ffmpeg -version
npx @emiyakatuz/crispasr-agent-transcriber@latest install
The installer:
~/plugins/crispasr-agent-transcriber;Download the recommended local English, Chinese, and language-detection bundle:
npx @emiyakatuz/crispasr-agent-transcriber@latest models
The command downloads only approved GGUF files into:
~/plugins/crispasr-agent-transcriber/models/
Then verify the installation:
npx @emiyakatuz/crispasr-agent-transcriber@latest doctor
With a Codex build that supports plugin commands, run:
codex plugin add crispasr-agent-transcriber@personal
If the CLI has no codex plugin command, open the Codex desktop Plugins view
and install CrispASR Transcriber from the Personal marketplace. Start a new
conversation, then ask:
Transcribe C:\path\to\sample.mp4 with CrispASR using auto language detection.
Save a verbose JSON transcript and an SRT subtitle file.
npx @emiyakatuz/crispasr-agent-transcriber@latest update
npx @emiyakatuz/crispasr-agent-transcriber@latest uninstall
Uninstall preserves local models, CrispASR binaries, and outputs. Use
uninstall --purge-data only when those files should also be deleted. See
Plugin installation for manual installation and
troubleshooting.
After installation, you can run the transcription script without Codex:
Set-Location (Join-Path $HOME "plugins\crispasr-agent-transcriber")
uv run python scripts/transcribe.py sample.mp4 --profile auto `
--manage-server `
--models-dir models `
--format verbose_json
The MCP server is the cross-agent interface. Any agent that supports MCP stdio can run the released package directly from GitHub:
uvx --from "crispasr-agent-transcriber[mcp] @ git+https://github.com/EmiyaKatuz/[email protected]" crispasr-agent-mcp
Use the same command and arguments in Claude Desktop, Cursor, or another MCP client. See AI agent integrations for a generic MCP configuration and Codex CLI command.
End users do not need the release steps. Maintainers should follow the publishing guide for Codex Marketplace, PyPI, MCP Registry, and cross-agent distribution.
Install/update never downloads models. Use the explicit models command or
download these three recommended GGUF files into a local directory such as
models/:
Optional model IDs include english-q5-0, english-q5-1, english-q6,
english-q8, english-f16, chinese-q8, chinese-f16, lid-q2, lid-q8,
and lid-f16. Download a specific option with:
npx @emiyakatuz/crispasr-agent-transcriber@latest models --model-id english-q8
All three upstream model families are Apache 2.0 licensed.
For automatic English/Chinese routing, pass both ASR paths. The language probe runs first, and only the matching model is loaded:
--english-model models\cohere-transcribe-q4_k.gguf
--chinese-model models\qwen3-asr-1.7b-q4_k.gguf
--lid-backend firered --lid-model models\firered-lid-q4_k.gguf
For an explicit english or chinese profile, --model remains available as
a single-model override.
The tool auto-detects, installs, and updates the CrispASR binary from GitHub releases.
When --manage-server is set and no binary is found, it auto-installs before
starting the server.
On install and update, the tool checks your hardware:
nvidia-smi available, or CUDA_PATH / CUDA_HOME set, or
CUDA in PATH -> downloads crispasr-*-cuda variant.vulkaninfo or VULKAN_SDK set (only when CUDA is absent) ->
downloads crispasr-*-vulkan variant.macOS always uses the universal binary.
auto mode runs FireRed language detection on the media, then routes English
to Cohere or Chinese to Qwen3-1.7B. Mixed or uncertain content stops with a
clear error asking you to re-run with --profile english or --profile chinese.
uv run python scripts/transcribe.py sample.wav `
--profile auto `
--manage-server `
--models-dir models `
--format srt `
--out-dir outputs
Add --keep-server to leave the server running after transcription.
# Terminal 1 -- start the server
crispasr --server --backend cohere `
-m models\cohere-transcribe-q4_k.gguf `
--port 8080
# Terminal 2 -- transcribe
uv run python scripts/transcribe.py sample.mp4 `
--profile english `
--server-url http://127.0.0.1:8080 `
--format verbose_json
If the running server's backend doesn't match the selected profile, the tool prints the exact command you need to start the correct server.
A .metadata.json sidecar is always written alongside the transcript.
Video files are detected automatically. ffmpeg extracts the audio track to a temporary mono 16 kHz WAV before sending it to CrispASR. The temporary file is deleted when transcription finishes.
--profile auto|english|chinese
--format text|verbose_json|srt|vtt|json
--out-dir PATH
--server-url URL
--allow-remote-server
--manage-server
--keep-server
--model PATH Local GGUF override for an explicit profile
--english-model PATH Cohere model selected after English detection
--chinese-model PATH Qwen3-ASR model selected after Chinese detection
--models-dir PATH Directory containing approved local GGUF models
--allow-model-auto-download
--lid-model PATH Local LID model path
--lid-backend firered|silero|ecapa|whisper
--host HOST Managed server host (default 127.0.0.1)
--port PORT Managed server port (default 8080)
--language CODE Language hint for transcription
--prompt TEXT Initial prompt/context
--vad Enable voice activity detection
--diarize Enable speaker diarization
--diarize-method METHOD
--hotwords WORD,WORD Comma-separated hotwords
--no-timestamps
--preprocess auto|always|never
--api-key KEY If CRISPASR_API_KEYS is enabled
--crispasr-bin-dir PATH
--crispasr-bin PATH
--install-crispasr
--update-crispasr
--crispasr-status
--list-models
--download-models
--model-id MODEL_ID
--overwrite-models
uv sync --extra mcp
uv run --extra mcp crispasr-agent-mcp
Exposed tools:
--server-url only accepts localhost
unless --allow-remote-server is explicitly passed.shell=False. No user-controlled strings are interpolated into shell
commands.-m auto) requires
--allow-model-auto-download. The models command and
crispasr_download_models tool download only allowlisted Hugging Face files.CrispStrobe/CrispASR GitHub releases.uv run pytest
uv run ruff check . # zero lint warnings
This project is licensed under the MIT License.
This tool orchestrates several independently-licensed projects. It does not bundle, fork, or redistribute their code -- it downloads pre-built binaries and calls them as subprocesses or HTTP services at runtime.
Model files must be downloaded separately by the user from their respective HuggingFace repositories. See Required models above.
Transcribe and understand local audio/video with CrispASR and local models only.
{ "mcpServers": { "io.github.emiyakatuz-crispasr-agent-transcriber": { "command": "uvx", "args": [ "crispasr-agent-transcriber==0.4.0" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
CrispASR Agent Transcriber 透過 stdio 在本機執行。
上次檢查時間:2026-11-09。 Transcribe and understand local audio/video with CrispASR and local models only.