- Home
- Transcription Software
- Picovoice Leopard
Picovoice Leopard
What it is
Picovoice Leopard is an on-device speech-to-text engine for transcribing audio and video recordings, including interviews, meetings, calls, podcasts, and voicemails. Picovoice says audio and generated transcripts stay on the device and are not transmitted to or accessible by the company or its service providers. Transcripts can include word start and end times, confidence scores, and speaker tags. Developers can use Picovoice Console to add vocabulary and raise the likelihood of selected words or phrases. Listed languages are English, French, German, Italian, Japanese, Korean, Portuguese, and Spanish. SDKs and quick starts cover Linux, macOS, Windows, Android, iOS, web, Raspberry Pi, and development frameworks. Use requires a Picovoice AccessKey, which authenticates requests and checks account limits; usage is measured by audio processed per second and resets every 30 days. Leopard does not handle real-time transcription. Pricing is available on request, and a 7-day trial is listed as free, with no credit card or auto-renewal.
For and against
For
- Processes audio and transcripts locally, according to Picovoice.
- Adds word timings, confidence scores, and speaker tags.
- Custom vocabulary can boost selected words and phrases.
- Supports eight listed languages.
- SDK quick starts cover multiple platforms and frameworks.
Against
- Does not support real-time transcription.
- Requires a Picovoice AccessKey and usage is account-limited.
- Paid pricing is available on request.
- No dedicated personal or non-commercial plans are listed.
The verdict
Leopard offers local transcription with word metadata and customizable vocabulary across a range of platforms. Its lack of real-time transcription and enterprise-focused positioning are important considerations.
Who it suits
Leopard suits developers building applications that transcribe recorded speech and need word-level timing or speaker tags. Picovoice describes its focus as enterprise on-device AI and says it has no dedicated personal or non-commercial plans.
Plans and prices
Free Trial
7 days · Access to all Picovoice products · No credit card required · No auto-renewal
Read 10 Oct 2026 · console.picovoice.ai
On the record
- Access and usage
- Using Picovoice requires an AccessKey, which authenticates and authorizes use and verifies that usage is within account limits.picovoice.ai · read 10 Oct 2026
- Access requirement
- Using Leopard requires a Picovoice AccessKey, which authenticates use and verifies it is within account limits.picovoice.ai · read 9 Oct 2026
- API access
- Yespicovoice.ai · read 20 Sep 2026
- Audience
- Picovoice describes itself as a B2B company focused on on-device AI for enterprises and says it has no dedicated plans for personal or non-commercial use.picovoice.ai · read 10 Oct 2026
- Customization
- Picovoice Console lets users add custom vocabulary, specify IPA pronunciations, and boost frequent words and phrases in speech-to-text models.picovoice.ai · read 10 Oct 2026
- Data use
- Picovoice says it cannot access, collect, or use end-user data to train or improve its AI models, except for custom development where a customer explicitly provides data under a separate written agreement.picovoice.ai · read 10 Oct 2026
- Free trial
- Picovoice offers enterprise developers a one-time free trial with no credit card required; it does not renew automatically.picovoice.ai · read 9 Oct 2026
- Integrations
- Picovoice provides Leopard SDK quick starts for Android, C, .NET, Flutter, iOS, Java, Linux, macOS, Node.js, Python, Raspberry Pi, React, React Native, web, and Windows.picovoice.ai · read 9 Oct 2026
- Intended users
- Picovoice describes itself as a B2B company focused on on-device AI tools for enterprises and says it has no dedicated plans for personal or non-commercial use.picovoice.ai · read 9 Oct 2026
- Languages
- Leopard supports English, French, German, Italian, Japanese, Korean, Portuguese, and Spanish; other languages are available to Enterprise Plan customers through Picovoice contacts.picovoice.ai · read 10 Oct 2026
- Local processing
- Leopard processes voice locally on the device.picovoice.ai · read 10 Oct 2026
- Purpose
- Leopard is an on-device speech-to-text engine for transcribing audio and video files, including recordings of interviews, meetings, calls, podcasts, and voicemails.picovoice.ai · read 10 Oct 2026
- Real-time limitation
- Leopard does not support real-time transcription; Picovoice directs users needing streaming transcription to Cheetah.picovoice.ai · read 9 Oct 2026
- SDK availability
- Leopard SDK quick starts are listed for Android, C, .NET, Flutter, iOS, Java, Linux, macOS, Node.js, Python, Raspberry Pi, React, React Native, Web, and Windows.picovoice.ai · read 10 Oct 2026
- Security
- Picovoice says end-user inputs and generated outputs remain on-device and are not transmitted to, stored by, or accessible to Picovoice or its service providers.picovoice.ai · read 10 Oct 2026
- Security and compliance
- Picovoice says it does not list security certifications because it cannot access audio processed by its engines or their outputs.picovoice.ai · read 9 Oct 2026
- Speaker identification
- Yespicovoice.ai · read 20 Sep 2026
- Support
- Enterprise customers can customize their support level, prospects can contact sales for dedicated support, and enterprise developers can report code or documentation issues on GitHub.picovoice.ai · read 10 Oct 2026
