Picovoice Leopard
picovoice.ai
What it is
Picovoice Leopard is an on-device speech-to-text engine for transcribing recordings, including interviews, meetings, calls, podcasts, voicemails, and video files. Picovoice says audio inputs and generated transcripts stay on the device and are not transmitted to, stored by, or accessible to the company or its service providers. Transcripts can include word-level start and end times, confidence scores, and speaker tags. Developers can use Picovoice Console to add custom vocabulary and raise the likelihood of selected words or phrases.
The listed languages are English, French, German, Italian, Japanese, Korean, Portuguese, and Spanish. Platforms include Android, iOS, Linux, macOS, Windows, web, and Raspberry Pi, with SDK quick starts for these and additional frameworks and languages. Use requires a Picovoice AccessKey, which verifies authorization and account limits; usage is measured by audio processed per second and resets every 30 days. Leopard does not support real-time transcription. Pricing is on request. The 7-day trial costs 0.00 USD, includes all Picovoice products, and requires no credit card.
Spec sheet
- What it does
- Leopard is an on-device speech-to-text engine for transcribing audio recordings.Read 9 Oct 2026 · picovoice.ai
- 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.Read 10 Oct 2026 · picovoice.ai
- 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.Read 9 Oct 2026 · picovoice.ai
- 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.Read 10 Oct 2026 · picovoice.ai
- Free plan
- NoRead 20 Sep 2026 · picovoice.ai
- 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.Read 9 Oct 2026 · picovoice.ai
- 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.Read 10 Oct 2026 · picovoice.ai
- 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.Read 10 Oct 2026 · picovoice.ai
- Access and usage
- Using Picovoice requires an AccessKey, which authenticates and authorizes use and verifies that usage is within account limits.Read 10 Oct 2026 · picovoice.ai
- Access requirement
- Using Leopard requires a Picovoice AccessKey, which authenticates use and verifies it is within account limits.Read 9 Oct 2026 · picovoice.ai
- API access
- YesRead 20 Sep 2026 · picovoice.ai
- Customization
- Picovoice Console lets users add custom vocabulary, specify IPA pronunciations, and boost frequent words and phrases in speech-to-text models.Read 10 Oct 2026 · picovoice.ai
- 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.Read 10 Oct 2026 · picovoice.ai
- Free trial
- Picovoice offers enterprise developers a one-time free trial with no credit card required; it does not renew automatically.Read 9 Oct 2026 · picovoice.ai
- Languages
- Leopard supports English, French, German, Italian, Japanese, Korean, Portuguese, and Spanish; other languages are available to Enterprise Plan customers through Picovoice contacts.Read 10 Oct 2026 · picovoice.ai
- Local processing
- Leopard processes voice locally on the device.Read 10 Oct 2026 · picovoice.ai
- Real-time limitation
- Leopard does not support real-time transcription; Picovoice directs users needing streaming transcription to Cheetah.Read 9 Oct 2026 · picovoice.ai
- 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.Read 10 Oct 2026 · picovoice.ai
- Security and compliance
- Picovoice says it does not list security certifications because it cannot access audio processed by its engines or their outputs.Read 9 Oct 2026 · picovoice.ai
- Speaker identification
- YesRead 20 Sep 2026 · picovoice.ai
- Supported platforms
- The SDK introduction lists Linux, macOS, Windows, Android, iOS, web, and Raspberry Pi as supported platforms.Read 9 Oct 2026 · picovoice.ai
- Timestamp support
- YesRead 20 Sep 2026 · picovoice.ai
- Usage limits
- Picovoice tracks Leopard usage by audio processed per second, and usage resets every 30 days.Read 10 Oct 2026 · picovoice.ai
- Word metadata
- Along with transcripts, Leopard can return each word’s start and end times, confidence, and speaker tag when diarization is enabled.Read 10 Oct 2026 · picovoice.ai
Plans and prices
Strong points and limits
Strong points
- Processes audio locally on the device
- Word timestamps, confidence scores, and speaker tags
- Custom vocabulary and phrase boosting
- Supports eight listed languages
- 7-day trial requires no credit card
Limits
- Does not support real-time transcription
- Requires a Picovoice AccessKey
- No dedicated plans for personal or non-commercial use
- Pricing is on request
Who it suits
Leopard suits developers and enterprises that need local transcription of recorded audio or video, including word-level metadata and speaker tags. It is not designed around real-time transcription.
Verdict
Leopard offers on-device transcription with word-level metadata and vocabulary customization across several platforms. Its key limitation is that it handles recordings rather than real-time transcription; pricing is on request.
Where Specifiction places it
- Transcription Software#21 of 468.4
- Speech-to-Text Software#18 of 358.4
- AI transcription tools#25 of 468.2
- Speech Recognition Software#18 of 328.4
- Transcription tools#22 of 288.0