GeneratingTranscriptionTranscribes audio into the input language. npmpnpmyarnbunnpm i @xsai/generate-transcription Examples Basic import { generateTranscription } from '@xsai/generate-transcription' import { openAsBlob } from 'node:fs' const { text } = await generateTranscription({ apiKey: '', baseURL: 'http://localhost:8000/v1/', file: await openAsBlob('./test/fixtures/basic.wav', { type: 'audio/wav' }), fileName: 'basic.wav', language: 'en', model: 'deepdml/faster-whisper-large-v3-turbo-ct2', }) Verbose + Segments import { generateTranscription } from '@xsai/generate-transcription' import { openAsBlob } from 'node:fs' const { duration, language, segments, text } = await generateTranscription({ apiKey: '', baseURL: 'http://localhost:8000/v1/', file: await openAsBlob('./test/fixtures/basic.wav', { type: 'audio/wav' }), fileName: 'basic.wav', language: 'en', model: 'deepdml/faster-whisper-large-v3-turbo-ct2', responseFormat: 'verbose_json', }) Verbose + Words import { generateTranscription } from '@xsai/generate-transcription' import { openAsBlob } from 'node:fs' const { duration, language, text, words } = await generateTranscription({ apiKey: '', baseURL: 'http://localhost:8000/v1/', file: await openAsBlob('./test/fixtures/basic.wav', { type: 'audio/wav' }), fileName: 'basic.wav', language: 'en', model: 'deepdml/faster-whisper-large-v3-turbo-ct2', responseFormat: 'verbose_json', timestampGranularities: 'word', })Edit on GitHubLast updated on SpeechGenerates audio from the input text.ImageCreates an image given a prompt.
xsAIxsAI