Transcribe base64 audio into text via the z-ai-web-dev-sdk.
npx skills add https://github.com/Kin3Xc/promoly --skill asr-kin3xc
Please help me install this Agent Skill. Skill: ASR Source: https://github.com/Kin3Xc/promoly/tree/main/skills/ASR Command: npx skills add https://github.com/Kin3Xc/promoly --skill asr-kin3xc
This Skill addresses the need to convert spoken audio into written text for searchable archives, accessibility, and voice-enabled apps.
To get started, deploy the backend SDK approach: create a ZAI instance and call audio.asr.create with a base64-encoded audio file to obtain the transcription.
High-intent search queries and answers about installing and using this skill.
To transcribe audio recordings into text, you pass a base64-encoded audio file to the backend speech-to-text service. This returns a text property containing the accurate transcription for your meetings or podcasts.
Speech-to-text transcription supports common audio formats including WAV and MP3. You encode these audio files as base64 data before sending them to the backend for processing.
Yes, you need a backend environment to run speech-to-text conversion because it requires the z-ai-web-dev-sdk. You instantiate a ZAI instance on the server to handle the audio processing.
You can use this for both real-time speech processing and batch transcription. It handles streaming speech-to-text alongside processing pre-recorded audio files and voice notes.
To start transcribing audio using the z-ai-web-dev-sdk, create a ZAI instance and call audio.asr.create with your base64-encoded audio file. This returns the transcribed text property.
TIAN0517Transcribe spoken audio from files or base64 inputs into text.
steipeteTranscribe local audio files to text or subtitles using the Whisper CLI.
nidhalboumaiza-0Transcribe base64-encoded audio into text using the z-ai-web-dev-sdk.
JOHNNYWHITEMIKETranscribe spoken audio into text using the local Whisper CLI.
