collectiveai-team/speaker-diarization-3

Segments an audio recording based on who is speaking

Capabilities

No capability data available

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`audio`	string(uri)	Audio file or url	`"https://replicate.delivery/pbxt/IZjTvet2ZGiyiYaMEEPrzn0xY1UDNsh0NfcO9qeTlpwCo7ig/lex-levin-4min.mp3"`	—
`max_speakers`	integer	Maximum number of speakers to diarize. Default: None	`—`	min: 1
`min_speakers`	integer	Minimum number of speakers to diarize. Default: None	`—`	min: 1
`num_speakers`	integer	Number of speakers to diarize. Default: infer	`—`	min: 1

audiostring

Audio file or url

Default: "https://replicate.delivery/pbxt/IZjTvet2ZGiyiYaMEEPrzn0xY1UDNsh0NfcO9qeTlpwCo7ig/lex-levin-4min.mp3"

max_speakersinteger

Maximum number of speakers to diarize. Default: None

min: 1

min_speakersinteger

Minimum number of speakers to diarize. Default: None

min: 1

num_speakersinteger

Number of speakers to diarize. Default: infer

min: 1

Version: 6e29843b8c1bUpdated: 7/25/20265.7K runs