What audio formats does the AWS Transcribe tool support?

The tool supports a wide range of common audio formats including MP3, MP4, WAV, FLAC, Ogg, WebM, and AMR.

How do I specify a different language for transcription?

You can use the -l or --language flag followed by the specific language code, such as 'nl-NL' for Dutch or 'de-DE' for German.

Can I use this for real-time transcription?

No, this skill is designed for batch transcription jobs where pre-recorded audio files are processed.

Do I need to manually upload files to S3 before transcribing?

No, the tool handles the S3 upload automatically. It can also delete the temporary S3 file after the transcription is complete if the cleanup flag is used.

Does it support multiple AWS environments?

Yes, you can use the -p or --profile flag to specify different AWS credential profiles and the -r flag to target specific regions.

AWS Transcribe Tool

Name: AWS Transcribe Tool
Author: dnvriend

bydnvriend

云基础设施

Transcribes audio files into text using Amazon Transcribe with support for over 60 languages and automated S3 management.

关于

The AWS Transcribe Tool skill provides a streamlined CLI interface for Amazon Transcribe, simplifying the process of converting audio files like MP3, WAV, and FLAC into text. It automates the complex workflow of uploading media to S3, initiating transcription jobs, monitoring progress, and downloading final transcripts, while offering advanced features like AWS profile management, automated S3 cleanup, and multi-level verbosity for debugging. This tool is ideal for developers and content creators who need a simple yet powerful way to handle batch audio transcription without the complexity of the standard AWS CLI.

主要功能

Advanced AWS profile and region management for multi-account workflows.
Support for 60+ languages with easy language code listing.
Automated S3 lifecycle management including upload and optional cleanup.
0 GitHub stars
Compatibility with multiple audio formats including MP3, WAV, FLAC, and Ogg.
Integrated OpenTelemetry support for observability and distributed tracing.

使用场景

Integrating speech-to-text capabilities into automated developer workflows and data pipelines.
Automating transcript generation for podcasts or video content hosted on AWS.
Converting meeting recordings or interviews into text documents for archival and search.

关于

主要功能

Advanced AWS profile and region management for multi-account workflows.
Support for 60+ languages with easy language code listing.
Automated S3 lifecycle management including upload and optional cleanup.
0 GitHub stars
Compatibility with multiple audio formats including MP3, WAV, FLAC, and Ogg.
Integrated OpenTelemetry support for observability and distributed tracing.

使用场景

Integrating speech-to-text capabilities into automated developer workflows and data pipelines.
Automating transcript generation for podcasts or video content hosted on AWS.
Converting meeting recordings or interviews into text documents for archival and search.