Recorded Overview

PreviousNext

Process recordings through the Batch path of Lanson Live API.

Batch is the recorded-audio path of Lanson Live API: submit a public audio_url, process asynchronously, and receive complete results. It is another workflow for Lanson Live, not a separate model to select.

For synchronous client-VAD clips see Segment Transcription. For live streams see Realtime.

How it works

Recorded Audio Batch Processing Workflow

When to use

ScenarioSuitable
Post-meeting processing✅
Batch audio file transcription✅
Need precise timestamps✅
Need structured results✅
Need subtitle files✅ (client-side from timestamps)
Short utterance after client VAD❌ use Segment
Live microphone stream❌ use Realtime

vs. Realtime and Segment

DimensionBatch jobsSegment HTTPRealtime
TransportHTTP asyncHTTP syncWebSocket
InputAudio URLMultipart filePCM16LE stream
LatencyMinutes~≤2.4sMilliseconds
OutputComplete JSONTranscript JSONEvent stream
SegmentationServer (time slice)Client (VAD)Server (VAD)
Success202 + poll200WS events

Current capabilities

CapabilityStatus
Full-file transcription✅
Segment timestamps✅
Confidence scores✅ (0 when upstream does not provide a value)
Translation✅ (per target language, frozen at job creation)
Webhook callback✅
LLM review correction✅ (on by default; set review: false to opt out)
Speaker diarizationComing soon
SRT/VTT subtitles✅ (client-side, generated from timestamps)

Next steps