Whisper Large v3
- multilingual
- word-timestamps
- translate
- Plans
- Every plan
- Typical run time
- ~20 s
Speech to textEvery planword-timestampscaptions
ElevenLabs Forced Alignment
ElevenLabs Forced Alignment: a speech to text model you can use in AutoReel.
At a glance
- Category
- Speech to text
- Produces
- json
- Typical run time
- ~15 s
- Plans
- Every plan, including Free
- Price
- Depends on the settings; shown before you generate
Parameters
The settings ElevenLabs Forced Alignment accepts. In the Studio they appear as a form with sensible defaults; through the API they’re the params of a generation.
audiostringrequired- Public URL of the audio recording to align. Supply a URL or upload an audio file. Maximum input: 10 hours and 3 GB.
promptstringrequired- The existing transcript spoken in the audio, not a generation instruction. Provide the text to align with the recording.
models
More speech to text models
Whisper Large v3 Turbo
- fast
- budget
- Plans
- Every plan
- Typical run time
- ~10 s
Whisper Large v3 (Video)
- video-input
- word-timestamps
- Plans
- Every plan
- Typical run time
- ~25 s
Make your first reel free
Sign up and get 100 credits to try every format: AI UGC videos, talking creators, slideshows and hook + demo reels. No card needed.