As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/nvidia-parakeet-canary/

# NVIDIA Parakeet / Canary / Nemotron Speech ASR (open)

NVIDIA, NeMo ASR family. Status: current. Type: speech and audio. Released: 2025-08-14.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `nvidia/parakeet-tdt-0.6b-v3` |  | https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3 |
| Hugging Face | `nvidia/canary-qwen-2.5b` |  | https://huggingface.co/nvidia/canary-qwen-2.5b |
| Hugging Face | `nvidia/parakeet-unified-en-0.6b` |  | https://huggingface.co/nvidia/parakeet-unified-en-0.6b |
| Hugging Face | `nvidia/nemotron-speech-streaming-en-0.6b` |  | https://huggingface.co/nvidia/nemotron-speech-streaming-en-0.6b |
| Hugging Face | `nvidia/nemotron-3.5-asr-streaming-0.6b` |  | https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b |
| NVIDIA NIM / build.nvidia.com |  |  | https://build.nvidia.com |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: audio
- Output: text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: cc-by-4.0 (Parakeet TDT v3, Canary-Qwen); NVIDIA Open Model License / OpenMDW (2026 models)

## Where it stands

- Newer speech and audio models in the registry since its release: 90. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- After it from NVIDIA: NVIDIA MagpieTTS Multilingual 357M (2025-12-11) https://postcutoff.com/m/nvidia-magpie-tts-multilingual/
- Weights are public. Licence: cc-by-4.0; NVIDIA Open Model License / OpenMDW. See the licence for commercial terms.

## What stands out

- Parakeet TDT 0.6B v3: 25 European languages, very high throughput: 600M FastConformer-TDT with auto language ID, punctuation, word timestamps, up to 24 min (3 h with local attention); 6.34% avg WER on Open ASR Leaderboard; trained on the Granary dataset. Source: https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3
- Canary-Qwen-2.5B speech-augmented LLM: FastConformer encoder + Qwen LLM (SALM); 5.63% mean WER topped the HF Open ASR Leaderboard at release (2025-07-17); can summarize/answer questions about the transcript. English, max 40 s clips. Source: https://huggingface.co/nvidia/canary-qwen-2.5b
- Cache-aware streaming ASR, 80-1120 ms chunks (found after launch): Nemotron Speech Streaming EN 0.6B (Jan/Mar 2026) and Nemotron 3.5 ASR Streaming 0.6B (June 2026, 40 language-locales) switch latency at inference without retraining; Parakeet-unified-en-0.6B (2026-04-07) does both offline (5.91% WER) and streaming down to 160 ms. Source: https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b

## Notes

One file for NVIDIA's open ASR family. Also canary-1b-v2 (European ASR + translation) and parakeet-tdt-0.6b-v2 (English, NIM). Nemotron 3.5 ASR HF card shows a garbled date; June 2026 per NVIDIA/press. NVIDIA's open TTS: magpie_tts_multilingual_357m. Full-duplex model: see nemotron-voicechat.

Sources: https://huggingface.co/collections/nvidia/nemotron-speech , https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3 , https://huggingface.co/nvidia/canary-qwen-2.5b

Model page: https://postcutoff.com/m/nvidia-parakeet-canary/