davideuler/local-whisper-input

github.com/davideuler/local-whisper-input ↗

Python

17 environment variables found in .env.example

Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow.

SERVICE_PLATFORM 密钥配置（必填）语音转录平台（siliconflow / groq / local）
LOCAL_MODEL 本地模型选择（SenseVoiceSmall / WhisperBase / WhisperV2Large / WhisperV3Large）
LOCAL_SENSEVOICE_MODEL_DIR 本地 SenseVoiceSmall 模型目录（ONNX 版本）
ENABLE_LOCAL_TRANSLATION 是否启用本地翻译功能（需要配置 SILICONFLOW_API_KEY）
SILICONFLOW_API_KEY secret 硅基流动 API 密钥 https://cloud.siliconflow.cn/account/ak
SILICONFLOW_TRANSLATE_MODEL 硅基流动翻译模型
GROQ_API_KEY secret GROQ API 密钥 https://console.groq.com/keys
GROQ_BASE_URL GROQ API 基础 URL
SYSTEM_PLATFORM 平台配置（必填）平台配置macos:mac / windows:win
TRANSCRIPTIONS_BUTTON 功能配置（必填）转录按钮配置 Mac 上 option 对应就是 alt）/ windows 上推荐配置诸如 f2/f5 等按钮（注意 f 为小写）
TRANSLATIONS_BUTTON 翻译按钮配置(与转录按钮组合使用)
CONVERT_TO_SIMPLIFIED 是否将繁体中文转换为简体中文 (true/false)
ADD_SYMBOL 是否为输入的文本添加标点符号 (true/false)
OPTIMIZE_RESULT 是否优化识别结果 (true/false), 实验性功能，可能会导致输入结果不准确
KEEP_ORIGINAL_CLIPBOARD 是否保留原始剪贴板内容，默认为 true
GROQ_ADD_SYMBOL_MODEL 模型配置（必填）为输入的文本添加标点符号的模型 (推荐 llama3-8b-8192/gemma2-9b-it/llama-3.3-70b-versatile/mixtral-8x7b-32768)
GROQ_OPTIMIZE_RESULT_MODEL 优化识别结果的模型 (推荐 llama3-8b-8192/gemma2-9b-it/llama-3.3-70b-versatile/mixtral-8x7b-32768)

Best match Fly.io Anything Dockerized — requires the Fly CLI.

macOS

brew install flyctl && fly launch --from https://github.com/davideuler/local-whisper-input

Linux

curl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/davideuler/local-whisper-input

Windows (PowerShell)

iwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/davideuler/local-whisper-input

Alternative Deploy on Railway Apps that need Postgres, Redis, or background workers.

Or deploy to a different host

Render Full-stack with managed Postgres + Redis. DigitalOcean App Platform Containers, droplets, and managed services.

← Try another repo