# NVIDIA Parakeet / Riva Review

> NVIDIA Parakeet / Riva review: Open-weights, GPU-accelerated self-hosted STT stack. Verified pricing, features, and the strongest alternatives in.

![NVIDIA Parakeet / Riva logo](https://www.versusref.com/logos/nvidia-parakeet.png)

Open-weights, GPU-accelerated self-hosted STT stack

Among the 43 speech-to-text tools we track, NVIDIA Parakeet / Riva has the 31st-widest language coverage.

See pricing · facts verified Jul 20, 2026

## What we know about NVIDIA Parakeet / Riva

This is our verified profile of NVIDIA Parakeet / Riva, a speech-to-text apis platform - open-weights, GPU-accelerated self-hosted STT stack. Every fact about NVIDIA Parakeet / Riva below carries the source it came from and the day we checked it.

NVIDIA Parakeet / Riva does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current NVIDIA Parakeet / Riva quote, it is the fastest way for us to close that gap.

On capabilities, NVIDIA Parakeet / Riva covers language auto-detection, word-level timestamps, custom vocabulary / keyterm boosting, speech translation, and self-host / on-prem option, and does not offer websocket streaming api. Each of those is verified against NVIDIA Parakeet / Riva's own docs or dashboard, not marketing copy.

Among the 43 speech-to-text tools in our matrix, NVIDIA Parakeet / Riva leads with the 31st-widest language coverage; the fact sheet below has the raw numbers behind that placement.

In total we track 21 verified facts for NVIDIA Parakeet / Riva today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the NVIDIA Parakeet / Riva fact sheet below.

## Fact sheet

### Pricing

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Pricing model | hybrid | Jul 20 | [source](https://www.nvidia.com/en-us/data-center/products/ai-enterprise/) |
| Free tier quota | Free hosted trial APIs on build.nvidia.com | Jul 20 | [source](https://developer.nvidia.com/riva) |

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| WER (third-party benchmark) | 6.43 % WER | Jul 20 | [source](https://artificialanalysis.ai/speech-to-text) |
| WER (vendor-claimed) | ~6.34 % WER | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |
| Languages supported | 25 | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |
| Language auto-detection | ✓  Yes | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |
| Speaker diarization | ✓  Included | Jul 20 | [source](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/asr/asr-overview.html) |
| Word-level timestamps | ✓  Yes | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |
| Custom vocabulary / keyterm boosting | ✓  Yes | Jul 20 | [source](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/asr/asr-overview.html) |
| Speech translation | ✓  Yes | Jul 20 | [source](https://huggingface.co/nvidia/canary-1b-v2) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://developer.nvidia.com/riva) |
| Model weights license | CC-BY-4.0 | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | Python, Go clients; gRPC protos; CLI clients | Jul 20 | [source](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/asr/asr-overview.html) |
| Max file size / duration | 24 min full attention; up to 3 hr with local attention | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |
| Supported audio formats | WAV, FLAC (16 kHz mono); Opus streams in Riva | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |
| Websocket streaming API | ✗  No | Jul 20 | [source](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/asr/asr-overview.html) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | Parakeet TDT 0.6B (600M); Canary 1B v2 (978M) | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |
| Hardware to self-host | NVIDIA GPU (T4 to H100); min 2GB RAM | Jul 20 | [source](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) |
| Hosted API available | Free trial NIM endpoints on build.nvidia.com | Jul 20 | [source](https://developer.nvidia.com/riva) |
| Project maintenance status | Active - NeMo v2.7.3 released 2026-04-23 | Jul 20 | [source](https://github.com/NVIDIA/NeMo) |
| GitHub stars | 17,800 | Jul 20 | [source](https://github.com/NVIDIA/NeMo) |

## NVIDIA Parakeet / Riva head-to-head

| Comparison | Record | Per use case |
| --- | --- | --- |
| [NVIDIA Parakeet / Riva vs OpenAI Whisper (API)](https://www.versusref.com/stt/nvidia-parakeet-vs-whisper/) | won 4 · lost 2 · tied 1 | Call Centers: won; Developers: lost; Dictation: won; Medical: lost; Meetings: won; Self-Hosted: won; Voice Agents: tie |
| [NVIDIA Parakeet / Riva vs Deepgram](https://www.versusref.com/stt/deepgram-vs-nvidia-parakeet/) | won 1 · lost 3 · tied 1 | Developers: lost; Dictation: tie; Medical: lost; Self-Hosted: won; Voice Agents: lost |

Source: https://www.versusref.com/stt/tools/nvidia-parakeet/