One API to query, transcribe, and monitor any public audio in real time
— ranked, timestamped, and speaker-attributed results, optimized for LLMs. In milliseconds.
API Natural-language query in, ranked audio clips out — embedding, ANN search, and rerank in between.
Trusted by teams building the next generation of audio-aware AI
Four core capabilities, one API surface. No stitching together pipelines.
Query by meaning, not keywords. Sonar finds the clips where your concept is discussed, even when the exact words aren't used.
Every result includes identified speakers with confidence scores and links directly to the exact moment in the source. Agents cite who said it, when, and the precise clip — not just the episode.
Breaking broadcasts, live hearings, and real-time podcasts are indexed within minutes of airing. Agents stay current.
Submit any public audio URL and get back a fully speaker-diarised, timestamped transcript in seconds. Ideal for agents that need to reason over specific recordings not yet in the Sonar index.
The Computer Chronicles (1984)
Spoken language is disfluent, non-linear, and speaker-dependent. We explain the architecture choices that make semantic audio retrieval work where BM25 breaks down.
The biggest release yet. Real-time broadcast monitoring, improved speaker diarisation accuracy, and a new streaming endpoint that fires every three seconds.
We're releasing the evaluation suite we use internally. 4,200 queries across 18 audio domains. Every API provider can now be compared on the same standard.