---
title: "Speech to Text Conversion"
method: POST
path: "/ai/audio/v1/async/speech-to-text"
tags: ["Audio"]
---

# Speech to Text Conversion

`POST /ai/audio/v1/async/speech-to-text`

Returns Speech to Text Conversion to the provided webhook URI.

## Query parameters

- `webhook` string, uri, required

## Request body

- AsrInput
  - `contentUri` string, uri — Publicly facing uri
  - `encoding` 'Mpeg' | 'Mp4' | 'Wav' | 'Webm' | 'Webp' | 'Aac' | 'Avi' | 'Ogg', required — The encoding of the original audio
  - `languageCode` string, required — Language spoken in the audio file.
  - `source` string — Source of the audio file eg: Phone, RingCentral, GoogleMeet, Zoom etc
  - `audioType` 'CallCenter' | 'Meeting' | 'EarningsCalls' | 'Interview' | 'PressConference' | 'Voicemail' — Type of the audio
  - `separateSpeakerPerChannel` boolean — Indicates that the input audio is multi-channel and each channel has a separate speaker.
  - `speakerCount` integer — Number of speakers in the file, omit parameter if unknown
  - `speakerIds` string[] — Optional set of speakers to be identified from the call.
  - `enableVoiceActivityDetection` boolean — Apply voice activity detection.
  - `enablePunctuation` boolean — Enables Smart Punctuation API.
  - `enableSpeakerDiarization` boolean — Tags each word corresponding to the speaker.
  - `speechContexts` SpeechContextPhrasesInput[] — Indicates the words/phrases that will be used for boosting the transcript. This can help to boost accuracy for cases like Person Names, Company names etc.
    - `phrases` string[], required — Words or Phrases to boost

## Response `202`

Task accepted for processing.

- CaiAsyncApiResponse
  - `jobId` string

## Other responses

- `400` — Bad Request

---

[API](https://skmtc.net/ringcentral/apis/ringcentral-api.md) · [All operations](https://skmtc.net/ringcentral/apis/ringcentral-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/ringcentral/ringcentral-api/revisions/8d602198ec97/schema)