Transcribe audio
AssemblyAI Transcribe Audio is a powerful AI-driven tool designed to convert audio and media files into accurate, easy-to-read transcripts accessible via a URL. It supports multiple languages and offers advanced features to enhance transcription quality and usability.
Features
- Supports transcription from any media file accessible via a URL.
- Multiple language options including English (US, UK, Australia), Spanish, French, German, Italian, Portuguese, Dutch, Hindi, and Japanese.
- Automatic punctuation for improved readability of transcripts.
- Speaker diarization to distinguish different speakers in the transcript.
- Optional advanced features like content safety moderation and sentiment analysis.
Benefits
- Quickly generate accurate transcriptions from audio or video files without manual effort.
- Enhances content accessibility by providing readable and searchable transcripts.
- Improves content moderation and compliance with built-in safety features.
- Enables detailed analysis with sentiment detection and speaker identification.
- Flexible integration options including webhooks and callback reruns for seamless automation.
Description
Create a transcript from a media file that is accessible via a URL. See the documentation
Parameters
8 parameters
| Name | Type | Description |
|---|---|---|
| urlrequired | string | The URL of your media file to transcribe. |
| languageCode | enum | The language of your audio file. The default value is |
| punctuate | boolean | Enable Automatic Punctuation |
| speakerLabels | boolean | Enable Speaker diarization |
| contentSafety | boolean | Enable Content Moderation |
| sentimentAnalysis | boolean | Enable Sentiment Analysis |
| webhookUrl | string | The URL we should send webhooks to when your transcript is complete |
| callbackWithRerun | boolean | Use the |