Transcribe MP3, WAV, OGG, M4A, and WebM audio files via the Telnyx Speech-to-Text API.
npx skills add https://github.com/team-telnyx/telnyx-toolkit --skill telnyx-stt
Please help me install this Agent Skill. Skill: telnyx-stt Source: https://github.com/team-telnyx/telnyx-toolkit/tree/main/tools/stt Command: npx skills add https://github.com/team-telnyx/telnyx-toolkit --skill telnyx-stt
This Skill converts audio recordings into written text, making spoken content searchable and editable.
Transcribe the audio file located at /path/to/audio.mp3 using the telnyx-stt script.
High-intent search queries and answers about installing and using this skill.
Transcribe audio recordings into text by sending MP3, WAV, OGG, M4A, or WebM files to the Telnyx Speech-to-Text API powered by Whisper. This converts spoken content into searchable and editable written text.
Supported audio formats for speech-to-text conversion include MP3, WAV, OGG, M4A, and WebM. The Skill processes these common file types to generate accurate written transcriptions of recorded spoken content.
You need the TELNYX_API_KEY environment variable configured to authenticate audio transcription requests. This key allows the Skill to securely access the Telnyx Speech-to-Text API powered by Whisper.
Convert voicemails and meeting recordings to text using the Telnyx Speech-to-Text API with Whisper. This method accurately transcribes recorded audio files into editable text for easy content review and analysis.
Transcribe customer service calls using the Whisper-powered Telnyx Speech-to-Text API. The Skill accepts common audio formats like WAV and MP3 to convert recorded calls into readable text for analysis.
Speech-to-text transcription requires the Telnyx API to leverage Whisper's speech recognition capabilities. This integration processes submitted audio files and returns accurate written text without requiring local model deployment.
pramudityadTranscribe audio files to plain text using the Groq Whisper API.
tarunccetConvert meeting transcripts into structured markdown summaries with decisions and action items.
team-telnyxProvides Go SDK examples for streaming Telnyx call audio to WebSockets or Dialogflow.
adbertramTranscribe local audio and video files into timestamped JSON transcripts using whisper.cpp.
