# Picovoice (Leopard / Cheetah) Review

> Picovoice (Leopard / Cheetah) review: Private, on-device STT SDK for apps and edge devices. Verified pricing, features, and the strongest alternatives in.

![Picovoice (Leopard / Cheetah) logo](https://www.versusref.com/logos/picovoice.png)

Private, on-device STT SDK for apps and edge devices

Among the 43 speech-to-text tools we track, Picovoice (Leopard / Cheetah) has the 38th-widest language coverage.

See pricing · facts verified Jul 20, 2026

## What we know about Picovoice (Leopard / Cheetah)

This is our verified profile of Picovoice (Leopard / Cheetah), a speech-to-text apis platform - private, on-device STT SDK for apps and edge devices. Every fact about Picovoice (Leopard / Cheetah) below carries the source it came from and the day we checked it.

Picovoice (Leopard / Cheetah) 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 Picovoice (Leopard / Cheetah) quote, it is the fastest way for us to close that gap.

On capabilities, Picovoice (Leopard / Cheetah) covers word-level timestamps, custom vocabulary / keyterm boosting, and self-host / on-prem option, and does not offer websocket streaming api. Each of those is verified against Picovoice (Leopard / Cheetah)'s own docs or dashboard, not marketing copy.

Placed against the 43 speech-to-text tools we track, Picovoice (Leopard / Cheetah)'s strongest showing is the 38th-widest language coverage - a spread worth weighing against your own priorities.

In total we track 13 verified facts for Picovoice (Leopard / Cheetah) 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 Picovoice (Leopard / Cheetah) fact sheet below.

## Fact sheet

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| WER (vendor-claimed) | ~9.7 % WER | Jul 20 | [source](https://github.com/Picovoice/speech-to-text-benchmark) |
| Languages supported | 8 | Jul 20 | [source](https://picovoice.ai/docs/leopard/) |
| Speaker diarization | ✓  Included | Jul 20 | [source](https://picovoice.ai/docs/api/leopard-python/) |
| Word-level timestamps | ✓  Yes | Jul 20 | [source](https://picovoice.ai/docs/api/leopard-python/) |
| Custom vocabulary / keyterm boosting | ✓  Yes | Jul 20 | [source](https://picovoice.ai/docs/leopard/) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://picovoice.ai/docs/leopard/) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | Python, C, Java, .NET, Node.js, iOS, Android, Web | Jul 20 | [source](https://picovoice.ai/docs/leopard/) |
| Supported audio formats | 3gp, FLAC, MP3, MP4/m4a, Ogg, WAV, WebM | Jul 20 | [source](https://picovoice.ai/docs/api/leopard-python/) |
| Websocket streaming API | ✗  No | Jul 20 | [source](https://picovoice.ai/docs/cheetah/) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | Leopard ~37 MB, Cheetah ~34 MB model files | Jul 20 | [source](https://github.com/Picovoice/speech-to-text-benchmark) |
| Hardware to self-host | CPU-capable incl. Raspberry Pi 3+; optional GPU | Jul 20 | [source](https://github.com/Picovoice/leopard) |
| Project maintenance status | Active - Cheetah v4.1.0 released 2026-06-24 | Jul 20 | [source](https://github.com/Picovoice/cheetah/releases) |
| GitHub stars | 669 | Jul 20 | [source](https://github.com/Picovoice/cheetah) |

Source: https://www.versusref.com/stt/tools/picovoice/