返回首页
Lanson Flow 文档库

Recorded Overview

Recorded is batch transcription: submit a public audio_url, process asynchronously, receive complete results.

For synchronous client-VAD clips see [Segment Transcription](/docs/api-reference/segment-transcription). For live streams see [Realtime](/docs/realtime).

How it works

Submit audio URL (POST /v1/audio/transcriptions/jobs)
  → Probe audio format and duration
  → Slice into time-based chunks
  → Concurrent transcription
  → Aggregate (merge into global timestamps)
  → Optional LLM review
  → Webhook callback (optional)

When to use

| Scenario | Suitable | |---|---| | Post-meeting processing | ✅ | | Batch audio file transcription | ✅ | | Need precise timestamps | ✅ | | Need structured results | ✅ | | Need subtitle files | ✅ | | Short utterance after client VAD | ❌ use [Segment](/docs/api-reference/segment-transcription) | | Live microphone stream | ❌ use [Realtime](/docs/realtime) |

vs. Realtime and Segment

| Dimension | Batch jobs | Segment HTTP | Realtime | |---|---|---|---| | Transport | HTTP async | HTTP sync | WebSocket | | Input | Audio URL | Multipart file | PCM16LE stream | | Latency | Minutes | ~≤1.6s | Milliseconds | | Output | Complete JSON | Transcript JSON | Event stream | | Segmentation | Server (time slice) | Client (VAD) | Server (VAD) | | Success | 202 + poll | 200 | WS events |

Current capabilities

| Capability | Status | |---|---| | Full-file transcription | ✅ | | Segment timestamps | ✅ | | Confidence scores | ✅ | | Translation | Coming soon | | Webhook callback | ✅ | | LLM review correction | ✅ (optional) | | Speaker diarization | Coming soon | | SRT/VTT subtitles | ✅ (generated from timestamps) |

Next steps

  • [Transcribe Audio](/docs/recorded/transcribe-audio) — submit a job
  • [Batch Jobs API](/docs/api-reference/batch-jobs)
  • [Segment API](/docs/api-reference/segment-transcription) — client-VAD clips
  • [Timestamps & Speakers](/docs/recorded/timestamps-speakers)