菜单
Speech-to-text via OmniRoute using OpenAI /v1/audio/transcriptions format with auto-fallback across Whisper, AssemblyAI, Deepgram, Azure STT. Use when the user wants transcription of audio files or real-time speech recognition.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/pablolira-1982/OminiRoute --skill omniroute-stt命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Analyze open feature request issues, implement viable ones on dedicated branches, and respond to authors
Create a new release, bump version up to the .10 patch threshold, update changelog, and manage Pull Requests
Manage the OmniRoute server lifecycle via CLI — start/stop/restart, non-interactive setup, diagnostics (omniroute doctor), backup/restore, autostart, and tunnel management. Use when the user wants to operate the OmniRoute server, automate provisioning, or troubleshoot the runtime.
基于 SOC 职业分类
正在显示 SKILL.md
| name | omniroute-stt |
| description | Speech-to-text via OmniRoute using OpenAI /v1/audio/transcriptions format with auto-fallback across Whisper, AssemblyAI, Deepgram, Azure STT. Use when the user wants transcription of audio files or real-time speech recognition. |
Requires OMNIROUTE_URL and OMNIROUTE_KEY. See entry-point SKILL for setup.
POST $OMNIROUTE_URL/v1/audio/transcriptions — multipart upload, returns textPOST $OMNIROUTE_URL/v1/audio/translations — transcribe + translate to Englishcurl $OMNIROUTE_URL/v1/models/stt | jq '.data[]'
curl -X POST $OMNIROUTE_URL/v1/audio/transcriptions \
-H "Authorization: Bearer $OMNIROUTE_KEY" \
-F "file=@audio.mp3" \
-F "model=whisper-1" \
-F "response_format=verbose_json"
Response: { text, language, duration, segments?:[{ start, end, text }] }
Audio: mp3, mp4, mpeg, mpga, m4a, wav, webm.
Response formats: json, text, srt, verbose_json, vtt.
400 invalid_file_format → unsupported audio format400 file_too_large → exceeds provider limit (usually 25MB)503 → provider unavailable; try another model in /v1/models/stt