Skip to main content

Precision-3

LatestOur most accurate diarization model, with tunable detection and frame-level probability scores.

Precision-2

Previous-generation high-accuracy diarization, and the current default.

Live-1

Streaming diarization over WebSocket for live audio.

Community-1

Open-source diarization for research, prototyping, and self-hosting.

​
Precision-3 migration

The rollout happens in two phases.

Today

Precision-3 is available as an opt-in model. Precision-2 remains the default. Set model: "precision-3" in your request to use it.

October 3

Precision-3 becomes the default for any request that does not explicitly set a model.

October 17

Precision-2 is deprecated. If you explicitly set model: "precision-2" today, plan to remove or update that value before then.
Action required before October 17. If your integration sets model: "precision-2" or reads the confidence output, it needs updating. Both are covered in the checklist below.

​
Model migration

If you explicitly set model: "precision-2" in your requests, update this value to "precision-3", or remove the parameter entirely to rely on the new default.

​
Confidence output deprecation

The confidence output is deprecated. It is not renamed to a single equivalent: it is replaced by three separate scores, each answering a narrower question. If your integration reads confidence, update it to read whichever of the three matches what you actually need before October 17. turnLevelConfidence has not changed.

​
Migration checklist

1

Replace or remove explicit model references

Replace or remove any explicit model: "precision-2" references.
2

Replace confidence reads

Replace reads of confidence with speakerProbability, speechProbability, or crosstalkProbability.
3

Confirm turn-level confidence

Confirm turnLevelConfidence usage still works as expected. No change is needed here.
4

Test a sample of your traffic

Test a sample of your traffic against Precision-3 before October 17, particularly if your audio is closer to clean read speech, telephone, or broadcast material.

​
Choosing the right model

​
Precision-3

Best for: Teams who want the highest diarization accuracy available, plus control over detection behaviour and access to frame-level probability scores. Precision-3 is 34.2% more accurate, on average, than Community-1.
Self-hosted options for Precision-3 are available on Enterprise plans. Self-hosted deployments also choose an operating mode per deployment — accuracy (14.3 average DER), balance (14.9) or speed (15.5). Operating modes are not available on the API.
Typical use cases: phone call analytics, meeting transcription with speaker attribution, video dubbing and timestamp-critical workflows, building training data for voice assistants, and more. Precision-3 provides optimization controls for workflows that need to tune detection to unusual audio conditions, or that consume probability curves directly: custom reconciliation with STT, and training data preparation pipelines. Advanced features:
  • Speaker identification with voiceprints: identify known speakers in your audio using pre-enrolled voiceprints
  • Exclusive diarization mode: returns diarization where only one speaker is active at a time, making STT reconciliation easier
  • Flexible speaker count control: set minSpeakers, maxSpeakers and numSpeakers for any number of speakers
  • Input controls: vadSensitivity and crosstalkSensitivity trade precision against recall for voice activity and overlapping speech
  • Frame-level probability scores: speechProbability, crosstalkProbability and speakerProbability sent every 20ms
Learn more about Precision-3

​
Precision-2

Best for: Existing integrations that have not yet moved to Precision-3. Deprecated on October 17. Precision-2 is 28% more accurate, on average, than Community-1. It remains the default model until Precision-3 takes over.
Self-hosted options for Precision-2 are available on Enterprise plans.
Typical use cases: phone call analytics, meeting transcription with speaker attribution, video dubbing and timestamp-critical workflows, building training data for voice assistants, and more. Advanced features:
  • Speaker identification with voiceprints: Identify known speakers in your audio using pre-enrolled voiceprints
  • Exclusive diarization mode: Returns speaker diarization where only one single speaker (the most likely to be transcribed) is active at a time, making STT reconciliation easier
  • Flexible speaker count control: Set minSpeakers, maxSpeakers and numSpeakers parameters for any number of speakers
  • Human-in-the-loop correction: Use confidence scores to help streamline manual correction processes
Learn more about Precision-2

​
Live-1

Best for: Teams building live voice products that need speaker labels before a recording finishes: contact centers, meeting tools, broadcast workflows, and real-time voice agents. Typical use cases: live meeting assistants, contact center agent assist, live captioning with speaker attribution, broadcast speaker attribution, and multi-party voice agents that need to track who is speaking. Advanced features:
  • Sub-300ms latency: Speaker labels arrive fast enough for live captioning and real-time agent assist, tested against noisy, real-world audio rather than clean studio recordings.
  • Native streaming architecture: Processes audio in 100ms chunks over WebSocket, with a speaker tracking layer that holds consistency across the stream without needing the full conversation.
  • Built for real conditions: Trained and validated on overlapping speech, background noise, and conversations with more than two participants.
Technical specs:
  • Up to 8 speakers, up to 5 hours duration per stream
  • Input: 16 kHz mono audio, 100ms chunks over WebSocket
  • Output: diarization_speaker_start and diarization_speaker_end events, each with a start or end timestamp and speaker label
Learn more about Live-1

​
Community-1 (hosted)

Best for: Teams who want the open-source model without managing infrastructure Typical use cases: Prototyping, low-volume production workloads, testing and validation Key Benefits:
  • Cost efficiency: hosted at cost, ideal for experimentation and low-volume workloads
  • No infrastructure management: Focus on your application while we handle the deployment
  • Easy migration: Start with hosted Community-1 and upgrade to Precision-3 when needed
  • Same powerful model: Access the same Community-1 model through our API without setup complexity
Learn more about Community-1

​
Community-1 (self-hosted with pyannote.audio 4.0)

Best for: Researchers, developers, and personal hobby projects who want full control over their diarization models and workflows. Typical use cases: Academic work, product-iteration, prototyping, and custom diarization deployment (e.g., dataset-specific fine-tuning or custom reconciliation with STT). Key Benefits:
  • Best open-source speaker diarization model available - outperforms pyannote.audio 3.1 across all key metrics
  • Open-source flexibility: Full transparency into model weights and code allowing local and offline training and inference.
Trade-offs:
  • Lower accuracy compared to Precision-2 and Precision-3
  • No support for advanced features like speaker identification and voiceprints
  • Requires deploying the model on your own infrastructure
Learn more about pyannote.audio 4.0

​
How to specify a model in diarization requests

When making a diarization request, you can specify which model to use using the model parameter:
By default, if you do not specify a model, the API will use the Precision-2 model. Set model explicitly to use Precision-3.
Precision-3 is opt-in until October 3, when it becomes the default. Precision-2 is deprecated on October 17. See Precision-3 migration for the full timeline.

​
Switch between models

You can easily switch between models by changing the model parameter:
  • "model": "precision-3" for Precision-3
  • "model": "precision-2" for Precision-2 (default)
  • "model": "community-1" for Community-1
Note: Speaker identification and voiceprint features are not available for Community-1 models. These advanced features are exclusive to Precision-2 and Precision-3.

​
Compare results between models

To compare performance between models on your specific data:
  1. Process the same audio file with both models
  2. Compare the diarization results
  3. Evaluate which model provides better accuracy for your use case

​
Pricing

For detailed pricing information, visit our pricing page.