Parakeet Tdt 0.6b

Purpose: Transcribing English speech recordings into text without relying on a proprietary hosted transcription service.

Inferred · not functionally tested

Audience: developers building speech transcription applications

Inferred · not functionally tested

Functions: speech_to_text

Inferred · not functionally tested

Interfaces: API: indicated (inferred, not tested) · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: API, CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: huggingface.co. These links do not verify the individual claims.

In the Speech to text space, Parakeet Tdt 0.6b takes a focused approach. Inferred · not functionally tested: It focuses on transcribing English speech recordings into text without relying on a proprietary hosted transcription service. Inferred · not functionally tested: Parakeet Tdt 0.6b is an open-source project aimed at developers building speech transcription applications. Basis unknown · not verified: The project is open source (Apache-2.0). Basis unknown · not verified: It runs on the command line, and it can be self-hosted.

Behind Parakeet Tdt 0.6b is NVIDIA, based in the United States, and it first shipped in 2019. The project is developed in the open on GitHub with 18.2k stars and 149 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 6 similar projects. Inferred · not functionally tested: Key capabilities include speech transcription, english recognition, and fastConformer encoder.

Summary written by a language model from the project’s public pages.