vsref
NVIDIA Magpie TTS logo

NVIDIA Magpie TTS

OSS

A small, GPU-efficient 9-language TTS checkpoint for teams already in the NVIDIA NeMo/Riva ecosystem; commercially usable open weights, but zero-shot voice cloning was removed from the open release and it caps generations at about 20 seconds.

Among the 46 text-to-speech tools we track, NVIDIA Magpie TTS has the 26th-widest language coverage.

See pricing

Facts verified Jul 20, 2026Website →

What we know about NVIDIA Magpie TTS

NVIDIA Magpie TTS is a text-to-speech apis platform: a small, GPU-efficient 9-language TTS checkpoint for teams already in the NVIDIA NeMo/Riva ecosystem; commercially usable open weights, but zero-shot voice cloning was removed from the open release and it caps generations at about 20 seconds. This profile tracks what we have verified about NVIDIA Magpie TTS, each fact linked to a primary source and dated.

NVIDIA Magpie TTS 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 Magpie TTS quote, it is the fastest way for us to close that gap.

On capabilities, NVIDIA Magpie TTS covers self-host / on-prem option, and does not offer instant voice cloning. Each of those is verified against NVIDIA Magpie TTS's own docs or dashboard, not marketing copy.

In total we track 11 verified facts for NVIDIA Magpie TTS today, and add coverage as the ingestion pass revisits it. Where a number is a vendor claim rather than our own measurement, it is labeled as such on the NVIDIA Magpie TTS fact sheet below, and each row links the primary source it came from so you can check our work.

Whether NVIDIA Magpie TTS is the right call depends on your use case more than any single spec, which is why the head-to-head verdicts below score it per scenario rather than crowning one overall winner. Use the fact sheet for the raw numbers, and the matchups for how NVIDIA Magpie TTS actually fares against the platforms buyers most often weigh it against.

Fact sheet

Capabilities
Capabilities facts
Instant voice cloning✗ NoJul 20
Languages supported9 languagesJul 20
Compliance & trust
Compliance & trust facts
Self-host / on-prem option✓ YesJul 20
Model weights licenseNVIDIA Open Model License AgreementJul 20
Build experience
Build experience facts
Official SDKsNVIDIA NeMo Framework (Python) for local inferenceJul 20
Output formats22.05 kHz audio (neural codec output)Jul 20
Max input per requestUp to 20s speech per requestJul 20
Commercial
Commercial facts
Model size (parameters)357MJul 20
Hardware to self-hostNVIDIA A10, A30, A100, or H100 GPU; Linux preferredJul 20
Hosted API availableYesJul 20
Project maintenance statusActiveJul 20

Considering a switch? Best NVIDIA Magpie TTS alternatives →