parakeet-1.1b-rnnt-multilingual-asr

nvidia/parakeet-1_1b-rnnt-multilingual-asr

NVIDIA Build Card

High accuracy and optimized performance for transcription in 25 languages

Context Length

Not published

Input Pricing

$0.18 / 1M

Output Pricing

$0.18 / 1M

Recent Latency

No probes

Model Architecture & Limits

Canonical IDnvidia/parakeet-1_1b-rnnt-multilingual-asr

Publisher / Originatornvidia

Model FamilyParakeet

ArchitectureParakeet-RNNT (also known as FastConformer-RNNT) [1], [2] which is an optimized version of Conformer model [3] with 8x depthwise-separable convolutional downsampling with Hybrid loss <br> (Parakeet-RNNT-XXL-1.1B <br>)

Context Window LimitNot published

Max Output TokensNot published

Endpoint Protocolnim-custom

Capabilities & Modal Surfaces

Chat Conversation✕ No

Tool / Function Calling✕ No

Reasoning / Thinking✕ No

Structured Output (JSON)✕ No

Vision / Multimodal✕ No

Audio Processing✓ Yes

License & Restrictions

GOVERNING TERMS: The use of this model is governed by the NVIDIA Community Model License (found at https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/).

Commercial and research use permitted under governing model and API terms.