Actions20
- AI Scrape Actions
- Analyze Sentiment Actions
- Convert to SQL Actions
- Generate Embedding Actions
- HTML to Any Actions
- Image Generation Actions
- Make Prediction Actions
- NSFW Detection Actions
- Object Detection Actions
- Process Image Actions
- Profanity Detection Actions
- Search Web Actions
- Spam Detection Actions
- Speech to Text Actions
- Spell Check Actions
- Summary Actions
- Text to Speech Actions
- Translate Actions
- Translate Image Actions
- Web Suggestion Actions
Speech to Text → Speech to Text
AI-generatedOverview
This node performs speech-to-text transcription using the JigsawStack API. It supports processing audio from either a direct URL or a file stored in JigsawStack File Storage. The node can transcribe audio in various languages, optionally translate the transcription into English or another specified language, and identify different speakers in the audio. It also supports asynchronous processing via webhook and allows control over batch size for chunking audio during processing. This node is useful for converting spoken content into text for applications like transcription services, content analysis, or accessibility enhancements.
Use Case Examples
- Transcribing a podcast episode from a URL to generate searchable text content.
- Transcribing and translating a foreign language interview into English text.
- Separating speakers in a meeting recording to create speaker-specific transcripts.
- Using webhook URL to process large audio files asynchronously and receive results when ready.
Properties
| Name | Meaning |
|---|---|
| Audio Source | Choose the source of the audio, either a direct URL or a file store key in JigsawStack File Storage. |
| Audio URL | The URL of the audio file to process, required if Audio Source is set to URL. |
| File Store Key | The key used to retrieve the audio file from JigsawStack File Storage, required if Audio Source is set to File Store Key. |
| Language | Language code for transcription (e.g., en, es, fr). Leave blank for auto-detection. |
| Translate | Whether to translate the transcribed content into English or the specified language. |
| By Speaker | Whether to identify and separate different speakers in the audio file. |
| Webhook URL | Webhook URL to send the transcription result to asynchronously. If provided, processing is asynchronous. |
| Batch Size | The batch size to return, controlling how the audio is chunked for processing. Maximum is 40. |
| Request Options | Additional request options such as batching, SSL certificate validation, proxy, and timeout settings. |
Output
JSON
transcription- The transcribed text from the audio.translation- The translated text if translation was requested.speakers- Information about different speakers if speaker separation was enabled.status- Processing status, especially relevant if asynchronous processing via webhook is used.
Dependencies
- JigsawStack API key credential
Troubleshooting
- Ensure the audio URL or file store key is valid and accessible; invalid or inaccessible audio sources will cause errors.
- If using webhook URL, ensure the URL is reachable and can accept POST requests to receive asynchronous results.
- Batch size should not exceed the maximum allowed (40); exceeding it may cause request failures.
- Check network connectivity and proxy settings if requests fail due to network issues.
- If SSL certificate validation is disabled, be aware of potential security risks.