daanelson/whisperx

Accelerated transcription of audio using WhisperX

Capabilities

No capability data available

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`audio` *	string (uri)	Audio file	`—`	—
`align_output`	boolean	Use if you need word-level timing and not just batched transcription. Only works for English atm	`false`	—
`batch_size`	integer	Parallelization of input audio transcription	`32`	—
`debug`	boolean	Print out memory usage information.	`false`	—
`only_text`	boolean	Set if you only want to return text; otherwise, segment metadata will be returned as well.	`false`	—

audio required string

Audio file

align_output boolean

Use if you need word-level timing and not just batched transcription. Only works for English atm

Default: false

batch_size integer

Parallelization of input audio transcription

Default: 32

debug boolean

Print out memory usage information.

Default: false

only_text boolean

Set if you only want to return text; otherwise, segment metadata will be returned as well.

Default: false

Version: 9aa6ecadd306 Updated: 2/26/2026 94.4K runs