Octopus
Speech-to-Index

deep voice search powered by direct acoustic indexing

Start Building
Talk to Sales

Accurate

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]

Octopus Speech-to-Index accuracy compared to Google speech recognition.
Octopus Speech-to-Index cost compared to Google ASR.

Cost-Effective

10x to 22x more cost-effective compared to cloud-based speech recognition APIs. [1] [2]

Private

All voice data is processed on-device. Intrinsically HIPAA and GDPR compliant.

Reliable

100% of the voice recognition is on-device. No concurrency limit. No downtime.

Free Tier

100 hours of free transcription per month. No credit card is required.

Try it!

Loading Demo...

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