You can now orchestrate pyannoteAI Precision‑2 diarization models with the OpenAI Whisper Large V3 Turbo STT model. Combining best‑in‑class speaker attribution with state‑of‑the‑art multilingual transcription.

What it does:

Aligns speaker diarization and transcription into a unified workflow powered by the Whisper Large V3 Turbo model.

Technical details:

• Connects to OSS transcription model: OpenAI Whisper Large V3 Turbo

• Integrates seamlessly with pyannoteAI Precision‑2 diarization models

• Returns structured speaker‑attributed transcripts with timestamps and text

Use case:

Leverage Whisper’s support for 99 languages to cover broader use cases and deployment scenarios.

Generate clean, speaker‑attributed transcripts in a single API call.

👉 Explore technical documentation and tutorials: docs.pyannote.ai/tutorials/speech-to-text-diarization