api-asr

Transcribe audio and video to text using Volcengine ASR.

27|9|Updated Jan 25, 2026

Search Tags:#streaming #transcription #asr #speech-recognition #volcengine #hotword

Ready to run

npx skills add https://github.com/Leoyishou/personal-ai-company --skill api-asr-leoyishou

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: api-asr
Source: https://github.com/Leoyishou/personal-ai-company/tree/main/claude-global/skills/api-asr
Command: npx skills add https://github.com/Leoyishou/personal-ai-company --skill api-asr-leoyishou

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, requests_toolbelt, and includes scripts (resource) components.

What problem does it solve?

Transcribes audio and video into accurate text using Volcengine's speech recognition services, enabling automation and accessibility.

Core Features & Use Cases

Streaming and batch transcription with support for short live audio, long recordings, and segmented processing.
Hotword boosting using boosting table ID or name for improved recognition of domain-specific terms.
Flexible integration with CLI/scripts for automation, including language, punctuation, and ITN options.

Quick Start

Provide the path to your audio or video file and choose a mode to begin transcription.

Frequently Asked Questions about api-asr

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe long audio recordings to text automatically?▼

Volcengine ASR supports streaming transcription for audio and video files, allowing you to turn speech into text. You provide the file path and select a streaming or upload mode to begin automated transcription.

Can I improve speech recognition accuracy for domain-specific terms?▼

You can improve speech recognition accuracy for domain-specific terms using hotword boosting. Provide a boosting table ID or name to help the ASR system recognize specialized vocabulary in your audio.

Do I need Volcengine credentials to use this speech recognition service?▼

Yes, you need Volcengine credentials and model parameters to perform accurate speech recognition. These credentials authenticate your requests to the Volcengine ASR service for transcription tasks.

What audio and video transcription options are available for automation pipelines?▼

Available transcription options for automation pipelines include streaming, segment, and upload workflows. You can configure language settings, punctuation controls, and ITN options via CLI scripts for automated media processing.

Does Volcengine ASR support punctuation controls and ITN options?▼

Yes, Volcengine ASR supports punctuation controls and ITN options for transcription. These features help format the transcribed text automatically, making it suitable for automated pipelines and voice-enabled applications.

What is the best way to transcribe live audio streams into text?▼

The best way to transcribe live audio streams into text is using the streaming transcription mode in Volcengine ASR. It handles short live audio efficiently, providing real-time speech-to-text conversion for applications.