Octopus achieves accuracies much higher than any existing Speech-to-Text engine. Including tier-1 offerings such as Google Speech-to-Text. Picovoice remains the only voice AI partner that backs its performance claims with open-source and reproducible benchmarks. [1]
All voice data is processed on-device. Intrinsically HIPAA and GDPR compliant.
100% of the voice recognition is on-device. No concurrency limit. No downtime.
100 hours of free transcription per month. No credit card is required.
octopus = pvoctopus.create('${ACCESS_KEY}')metadata = octopus.index_file('${PATH}')matches = octopus.search(metadata,['${PHRASE_A}', '${PHRASE_B}', ...])Build with Python
Octopus octopus = new Octopus.Builder("${ACCESS_KEY}").build(appContext);OctopusMetadata metadata = handle.indexAudioFile("${PATH}");HashMap <String, OctopusMatch[]> matches = handle.search(metadata,new HashSet<>(Arrays.asList("${PHRASE_A}", "${PHRASE_A}", ...)));Build with Android
let octopus = Octopus(accessKey: "${ACCESS_KEY}")let metadata = octopus.indexAudioFile(path: "${PATH}")let matches = octopus.search(metadata: metadata,phrases: ["${PHRASE_A}", "${PHRASE_A}", ...])Build with iOS
English
German
Deutsch
French
Français
Spanish
Español
Japanese
日本語
Korean
한국어
Portuguese
Português
Italian
Italiano