Transcribe device microphone speech into JSON text output.
npx skills add https://github.com/mikeyobrien/rho --skill stt
Please help me install this Agent Skill. Skill: stt Source: https://github.com/mikeyobrien/rho/tree/main/platforms/android/skills/stt Command: npx skills add https://github.com/mikeyobrien/rho --skill stt
Transcribes spoken input from the device microphone into text, enabling hands-free input, command recognition, and dictation without external services.
Speak into the device microphone to obtain a transcription. For example, say "What's on my calendar today?" and receive the transcription in the agent's response.
High-intent search queries and answers about installing and using this skill.
Transcription captures spoken input from your device microphone and converts it to text in real time. Speak clearly into the microphone, and the Skill outputs the transcription as JSON with the text in the 'result' field, enabling voice commands, dictation, and hands-free input without external services.
Yes, on-device transcription works for voice commands, dictation, and accessibility input across mobile apps and agent interfaces. The Skill requires microphone permission and, when using cloud services, network access. Output is immediate as JSON with the transcribed text.
On-device transcription requires microphone permission to capture audio input. If using cloud speech services, network access is also needed. No external dependencies or additional setup is required beyond these standard permissions.
Speech transcription outputs a JSON object containing the transcribed text in the 'result' field, structured as {"result": "transcribed text"}. This format integrates directly with agent responses and app workflows for further processing.
On-device transcription can function without cloud services, capturing and processing audio locally on your device. Cloud-based transcription requires network access for enhanced accuracy or advanced features, but the core microphone capture and basic transcription operates independently.
On-device transcription processes audio locally without external services, offering privacy and offline capability. Cloud-based approaches require network access but may provide enhanced accuracy. This Skill supports on-device operation for immediate, hands-free transcription across apps and agent interactions.
aviz85Stream microphone audio to ElevenLabs Scribe v2 Realtime and write transcribed text to a temporary file.
GitnappTranscribe spoken audio into text with timestamps using Whisper.
kaivyyTranscribe audio files with OpenAI Whisper and synthesize speech from text.
zhuangbiaoweiTranscribe audio in 99 languages and translate speech to English using OpenAI's Whisper model.
