Get started

Make the most of conversational speech with state of the art speaker diarization

Backed by 10+ years of academic research, our technology detects, segments, counts, and labels speakers, making transcription and analysis faster and more efficient.

Start today and discover our cutting edge speaker diarization models

Get started

STATE-OF-THE-ART

Discover the power
of speaker diarization

Our AI speaker diarization models accurately identify and separate speakers in audio recordings, providing valuable insights and improving productivity.

Explore our models

USE CASES

Discover how users leverage our AI model

Explore the ways in which pyannote users incorporate our technologies into their tech stack to deliver top-tier products

Smart meetings
Record & transcribe meetings, transforming discussions into actionable notes effortlessly.
Medias
Efficiently transcribe medias for streamlined editing.
Monitor content on social medias.
Call centers
Transcribe high volumes of calls for compliance, training, and quality purposes.
Voice cloning
Generate synthetic voices to facilitate the broad distribution of content created by businesses.
Dubbing, podcasting
Localize content, ensuring seamless integration of voice-over or subtitles.
LLM training
Generate annotated datasets tailored for training multimodal Large Language Models.
Academic research
Transcribing large-scale audio data set for multidisciplinary research.
Healthcare
Accurately transcribe consultations to enhance communication between patients and doctors.

Smart meetings
Record & transcribe meetings, transforming discussions into actionable notes effortlessly.
Medias
Efficiently transcribe medias for streamlined editing.
Monitor content on social medias.
Call centers
Transcribe high volumes of calls for compliance, training, and quality purposes.
Voice cloning
Generate synthetic voices to facilitate the broad distribution of content created by businesses.
Dubbing, podcasting
Localize content, ensuring seamless integration of voice-over or subtitles.
LLM training
Generate annotated datasets tailored for training multimodal Large Language Models.
Academic research
Transcribing large-scale audio data set for multidisciplinary research.
Healthcare
Accurately transcribe consultations to enhance communication between patients and doctors.

Our models are leveraged by numerous businesses,
from AI-first startups to established large corporates

Our models are leveraged by numerous businesses, from AI-first startups to established large corporates

Our models are leveraged by numerous businesses,
from AI-first startups to established large corporates

"@hbredin has been an incredible mentor to the community, pushing the boundaries of diarization."

Jean-Louis Queguiner
CEO, Gladia
"@hbredin is the MVP of diarization. Hard to beat #pyannote (trust me I tried)..."

Max Bain
whisperX
"The audio & video UI lets you label segments or transcribe. We even have experimental workflows for speaker diarization with a model in the loop, thanks to the awesome @hbredin and #pyannote"
Explosion
Explosion_ai
"pyannote seems to be the go-to for diarizarion, nicely done. Any thoughts on CoreML or other edge framework?"

Zach Nagengast
Argmax

"@hbredin has been an incredible mentor to the community, pushing the boundaries of diarization."

Jean-Louis Queguiner
CEO, Gladia
"@hbredin is the MVP of diarization. Hard to beat #pyannote (trust me I tried)..."

Max Bain
whisperX
"The audio & video UI lets you label segments or transcribe. We even have experimental workflows for speaker diarization with a model in the loop, thanks to the awesome @hbredin and #pyannote"
Explosion
Explosion_ai
"pyannote seems to be the go-to for diarizarion, nicely done. Any thoughts on CoreML or other edge framework?"

Zach Nagengast
Argmax

OPTIMIZED BY DESIGN

Next generation of pretrained pipelines reaches
state-of-the-art performances

Our optimized AI models accurately separates and identifies speakers in audio recordings, saving you time and effort.

x2 faster*

+ 20% accuracy*

*versus pyannote open source model

ENHANCED FEATURES

Maximize speaker diarization capabilities with our advanced features

Speaker diarization

Partition multi-speaker conversations into separate speakers

Speaker identification

Track specific speakers across multiple conversations using voiceprints

Overlapping speech

Flag when multiple speakers talk over each other

Change point detection

Mark speaker change points

Voice activity detection

Spot when anyone is speaking

Speaker separation

Isolate speech of overlapping speakers

Confidence score

Pinpoint the exact areas where human attention is required

Get started

Make the most of conversational speech with state of the art speaker diarization