Transcribe audio and video content
Salad Transcription API lets you generate accurate transcripts, captions, or subtitles for audio and video content using ASR models like Whisper.
- Transcribe long files of video or audio content
- Access industry-leading accuracy for insights from your favorite LLM like GPT
- Get support for common file formats, so you won’t need to convert your files
Transcribe long-form content up to two hours long via API.
Take your content global
- Transcribe with high accuracy using the industry-leading Whisper large v3 ASR model
- Get support for 97 different languages, including English, Spanish, Russian, Arabic, and more
That means you’ll be able to make your content globally accessible with captions and subtitles that ensure ADA compliance for audiences with disabilities.
Transcribe content in major languages to connect with audiences across the globe.
Accurately identify speakers
Even better, Salad Transcription API lets you differentiate between speakers and most accents to transcribe content with many speakers.
- Create sentence and word-level time codes for precise caption or subtitle timing
- Review the confidence scores of each word to gauge accuracy
- Generate SRT files for captions or subtitles that are ready to import into video editors and players
