OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Leopard

Leopard is Picovoice’s on-device speech-to-text library for transcribing spoken audio in applications, with documented SDKs and demos across multiple development environments.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Leopard — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Leopard when an application needs speech-to-text processing on-device and its listed languages and SDK environments fit the project. Account for the internet connection required to validate an AccessKey.

Who it is for

  • Developers adding local speech transcription to an application.
  • Teams building voice-to-text features or recorded-audio transcription workflows.
  • Developers who need documented SDK options for desktop, mobile, web or Raspberry Pi environments.

Documented uses

  • Transcribe spoken input locally within an application.
  • Convert an audio file into text using a documented demo.
  • Choose an SDK path for a supported development environment.
Before you choose

Requirements & limits

A valid Picovoice AccessKey is required. AccessKey validation needs internet connectivity even though voice recognition runs offline. The README refers to trial usage limits and directs users to Picovoice for continued use or limit changes.

  • The README lists English, French, German, Italian, Japanese, Korean, Portuguese and Spanish; additional languages are offered to commercial customers case by case.
  • Documented environments include Linux, macOS, Windows, Android, iOS, Chrome, Safari, Firefox, Edge and Raspberry Pi 3, 4 and 5.
  • The repository is licensed under Apache-2.0.
  • SDK and demo setup varies by environment; consult the corresponding repository instructions.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Transcribe an audio file with the Python demo

Run the documented Python demo to transcribe a local audio file.

Before you start

  • Python package installer pip3
  • A Picovoice AccessKey
  • An audio file and its file path
  • Internet connectivity to validate the AccessKey

Steps

  1. Install the demo package with the command below.

    Documented command
    pip3 install pvleoparddemo

  2. Run leopard_demo_file --access_key ${ACCESS_KEY} --audio_paths ${AUDIO_FILE_PATH}, replacing the placeholders with the AccessKey and audio-file path.

Expected outcome

The demo is configured to transcribe the specified audio file.

Guide limitations

  • The README describes this as a demo workflow, not a production integration.
  • Speech recognition runs locally, but AccessKey validation requires internet connectivity.
  • Listed language support is English, French, German, Italian, Japanese, Korean, Portuguese and Spanish; additional languages are available to commercial customers on a case-by-case basis.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
Picovoice/leopard · Official homepage title · retained in its source language
How we review sourcesSuggest a correction