Skip to content

Ai_Cf_Openai_Whisper_Large_V3_Turbo_Input

Defined in: node_modules/.pnpm/@cloudflare+workers-types@4.20251118.0/node_modules/@cloudflare/workers-types/index.ts:4289

audio: string

Defined in: node_modules/.pnpm/@cloudflare+workers-types@4.20251118.0/node_modules/@cloudflare/workers-types/index.ts:4293

Base64 encoded value of the audio data.


optional initial_prompt: string

Defined in: node_modules/.pnpm/@cloudflare+workers-types@4.20251118.0/node_modules/@cloudflare/workers-types/index.ts:4309

A text prompt to help provide context to the model on the contents of the audio.


optional language: string

Defined in: node_modules/.pnpm/@cloudflare+workers-types@4.20251118.0/node_modules/@cloudflare/workers-types/index.ts:4301

The language of the audio being transcribed or translated.


optional prefix: string

Defined in: node_modules/.pnpm/@cloudflare+workers-types@4.20251118.0/node_modules/@cloudflare/workers-types/index.ts:4313

The prefix it appended the the beginning of the output of the transcription and can guide the transcription result.


optional task: string

Defined in: node_modules/.pnpm/@cloudflare+workers-types@4.20251118.0/node_modules/@cloudflare/workers-types/index.ts:4297

Supported tasks are ‘translate’ or ‘transcribe’.


optional vad_filter: boolean

Defined in: node_modules/.pnpm/@cloudflare+workers-types@4.20251118.0/node_modules/@cloudflare/workers-types/index.ts:4305

Preprocess the audio with a voice activity detection model.