---
title: "Start Audio Stream Transcription"
method: POST
path: "/audio-stream/start"
tags: ["Audio Stream"]
---

# Start Audio Stream Transcription

`POST /audio-stream/start`

Start real-time audio stream transcription with AssemblyAI

## Request body

- object
  - `audio_url` string, required — Audio stream URL (RTMP or RTSP protocol)
  - `language_code` string — Language code for transcription
  - `punctuate` boolean — Add punctuation to the transcript
  - `format_text` boolean — Format text in the transcript
  - `language_detection` boolean — Enable automatic language detection
  - `language_confidence_threshold` number — Confidence threshold for language detection
  - `audio_start_from` integer — Start transcription from this timestamp (milliseconds)
  - `audio_end_at` integer — End transcription at this timestamp (milliseconds)
  - `multichannel` boolean — Enable multi-channel audio processing
  - `speech_models` string[] — Array of speech models to use
  - `speech_threshold` number — Speech detection threshold (0.0-1.0)
  - `disfluencies` boolean — Include disfluencies in the transcript
  - `speaker_labels` boolean — Enable speaker diarization
  - `speakers_expected` integer — Expected number of speakers
  - `sentiment_analysis` boolean — Enable sentiment analysis
  - `entity_detection` boolean — Enable entity detection
  - `auto_highlights` boolean — Enable automatic highlights extraction
  - `content_safety` boolean — Enable content safety detection
  - `iab_categories` boolean — Enable IAB category classification
  - `auto_chapters` boolean — Enable automatic chapter generation
  - `summarization` boolean — Enable automatic summarization
  - `summary_model` string — Model to use for summarization
  - `summary_type` string — Type of summary to generate
  - `custom_topics` boolean — Enable custom topic detection
  - `topics` string[] — Array of custom topics to detect
  - `redact_pii` boolean — Redact personally identifiable information
  - `redact_pii_sub` string — PII redaction substitution method
  - `redact_pii_policies` string[] — Array of PII policies to apply
  - `redact_pii_audio` boolean — Redact PII from audio
  - `redact_pii_audio_quality` string — Quality setting for PII audio redaction
  - `filter_profanity` boolean — Filter profanity from transcript
  - `custom_spelling` object[] — Array of custom spelling corrections
  - `speech_understanding` object — Speech understanding configuration

## Response `200`

Audio stream started successfully

- object
  - `code` string
  - `message` string
  - `data` object
    - `task_id` string
    - `message` string

---

[API](https://skmtc.net/memories/apis/screenplay-extraction-api.md) · [All operations](https://skmtc.net/memories/apis/screenplay-extraction-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/memories/screenplay-extraction-api/revisions/720c8c144ddc/schema)