Models & pricing / Models / CrisperWhisper 2.0

CrisperWhisper 2.0 Overview

CrisperWhisper 2.0 is an open-weight multilingual automatic speech recognition (ASR) system built on Whisper. It provides controllable transcription styles (verbatim or intended), highly accurate word-level timestamps, forced alignment, long-form transcription without chunk artifacts, and production-ready inference with speculative decoding.

Choosing a model

If you're unsure which model to use, start with CrisperWhisper 2.0 for complex agentic coding, reasoning, and enterprise workloads. For lightweight, low-latency autocomplete or edge tasks, consider smaller parameters.

All current Nyra Health models support text and multimodal input, multilingual reasoning, and structured tool calling. Models are available via API, cloud hosters, and open-weights download repositories.

Model Lineage & Specification

crisperwhisper-2-0 is Nyra Health's primary release in the crisperwhisper family.

DeveloperNyra Health
API Identifiercrisperwhisper-2-0
Parameters1.55B / 769M / 244M / 809M
Context Window30 seconds
LicenseCustom

CrisperWhisper 2.0 is an open-weight multilingual automatic speech recognition (ASR) system built on Whisper. It provides controllable transcription styles (verbatim or intended), highly accurate word-level timestamps, forced alignment, long-form transcription without chunk artifacts, and production-ready inference with speculative decoding.