Transcribe audio files via Doubao Seed-ASR 2.0 API with speaker diarization.
npx skills add https://github.com/vahnxu/doubao-asr --skill doubao-asr
Please help me install this Agent Skill. Skill: doubao-asr（豆包语音转写） Source: https://github.com/vahnxu/doubao-asr/tree/main Command: npx skills add https://github.com/vahnxu/doubao-asr --skill doubao-asr
This Skill automates audio transcription from recorded files using Doubao Seed-ASR 2.0, offering high-accuracy Chinese speech recognition and various transcription options.
To transcribe an audio file, use the command: python3 {baseDir}/scripts/transcribe.py /path/to/audio.m4a
High-intent search queries and answers about installing and using this skill.
To transcribe audio to text, run the provided transcription script with your audio file path. The Skill uses the Doubao Seed-ASR 2.0 API to convert recorded speech into accurate text transcripts automatically.
Yes, this speech recognition tool supports various Chinese dialects and over 13 languages. It uses the Doubao Seed-ASR 2.0 API to ensure high accuracy across different linguistic inputs.
Yes, audio transcription supports speaker diarization to identify and separate speakers, and it can export transcripts as SRT subtitle files for direct use in video production.
To optimize speed and cost for audio transcription, select between standard, express, and offpeak recognition tiers. Use the express tier for fast results on long meeting recordings.
Yes, the transcription process handles uploading your local audio files to Volcengine TOS automatically. This step is required before submitting the task to the Doubao Seed-ASR 2.0 API.
LeoyishouTranscribe audio and video to text using Volcengine ASR.
inference-shTranscribe audio files into text with timestamps using Whisper models.
ericfitzTranslate English text to a target language while preserving placeholders and formatting.
guoqiaoTranscribe audio files locally using MLX on Apple Silicon.
