@radzor/speech-to-text
Audio transcription using OpenAI Whisper or Deepgram APIs. Supports file upload, language detection, timestamps, and multiple output formats.
AI & MLv0.1.0typescriptpythonServerspeechtranscriptionwhisperdeepgramaudioaisttby Radzor
Install
View source on GitHub →$npx radzor@latest add speech-to-text
⚠ Constraints: Requires API key. Audio size limits: Whisper 25MB, Deepgram varies by plan. Server-side only.
Inputs
| Name | Type | Default | Description |
|---|---|---|---|
| provider* | 'openai' | 'deepgram' | — | Transcription provider to use. |
| apiKey* | string | — | API key for the selected provider.OPENAI_API_KEY |
| model | string | — | Model identifier (e.g. whisper-1, nova-2). |
| language | string | — | ISO 639-1 language code (e.g. en, fr). Auto-detected if omitted. |
provider*'openai' | 'deepgram'
Transcription provider to use.
apiKey