Transcribe audio files into text using the z-ai-web-dev-sdk speech recognition API.
npx skills add https://github.com/mukaddam-ali/Anadolu-Kitchen --skill asr-mukaddam-ali
Please help me install this Agent Skill. Skill: ASR Source: https://github.com/mukaddam-ali/Anadolu-Kitchen/tree/main/skills/ASR Command: npx skills add https://github.com/mukaddam-ali/Anadolu-Kitchen --skill asr-mukaddam-ali
High-intent search queries and answers about installing and using this skill.
Read the audio file with fs, convert it to a base64 string, and pass it to zai.audio.asr.create from the z-ai-web-dev-sdk. The response text field contains the transcription. The SDK must only run in backend code.
The ASR service supports WAV, MP3, M4A, FLAC, and OGG formats. For best accuracy, use a sample rate of 16kHz or higher with clear speech and minimal background noise.
No, the z-ai-web-dev-sdk must be used in backend code only. Importing it in client-side code will fail, so transcription logic should live in server-side routes or services such as an Express.js endpoint.
Empty results usually come from poor audio quality, unsupported formats, or unclear speech. Verify the file format is supported, reduce background noise, and check that the audio contains audible spoken content.
Files over roughly 100MB should be split into smaller segments before transcription. You can also cache results by hashing the audio buffer to avoid reprocessing duplicate files and reduce memory pressure.
felipesantiago-coderConvert base64 encoded audio files into written text transcriptions.
thanhquan3010Transcribe audio files into text using OpenAI models with speaker diarization.
obulaiGenerate speech from text and transcribe audio with speaker diarization.
J4JoshuaConvert operator speech into offline text transcription with Apple Silicon Whisper models.
