Recording audio and video content seems like a blast until you have to transcribe it. (“Unfortunately, my talking speed is way faster than my typing speed.”)
Since most transcription API services are so expensive, you’re stuck between shelling out big bucks or manually doing it all yourself.
If only there was a powerful transcription API that leveraged ASR models to accurately transcribe audio and video content in different languages.
Say hello to Salad Transcription API.
TL;DR
At-a-glance
Best for
Integrations
Allows Existing Accounts
Overview
Salad Transcription API helps teams convert large volumes of media into accurate transcripts, captions, or subtitles.
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
Generate and share accurate captions that account for multiple speakers, languages, and accents.
Your transcriptions, right at your fingertips
Once you connect Salad Transcription API, you can send instructions from your platform via JSON and receive transcripts in the same format as well.
- Define various parameters such as languages, word- or sentence-level timestamps, and more
- Include SRT outputs in your JSON responses to use alongside your content
In just a few clicks, you’ll receive a full transcript in JSON and SRT formats.
Using speech-to-text models, Salad Transcription API makes it easy to accurately transcribe your audio and video content for any use case.
Transcribe content without breaking the bank.
Get lifetime access to Salad Transcription API today!
Plans & features
Deal terms & conditions
- Lifetime access to Salad Transcription API
- All future Small Business Plan updates
- If Plan name changes, deal will be mapped to the new Plan name with all accompanying updates
- You must redeem your code(s) within 60 days of purchase
- Stack unlimited codes
- Each additional code beyond 10 increases transcription hours per month by 200 hours per month
- Reselling transcription hours is prohibited
60 day money-back guarantee. Try it out for 2 months to make sure it’s right for you!
Features included in all plans
- Built with Whisper-large-V3 as the core model
- Transcribe up to 2 hour audio/video files
- 97 languages (all current and future languages)
- Diarization (speaker recognition)
- Sentence/Word-level time codes
- Hallucination removal typical from Whisper-large-V3
- Transcripts, captions, and subtitles
- Supports audio (MP3, WAV, M4A, etc.)
- Supports video (MP4, AVI, WMV, MKV, WEBM, etc.)
- Automatic speech recognition
- JSON, SRT outputs
Recent Comments