https://github.com/emibcn/podcast2text
Proof of concept for transcribing podcasts into text using GCP Speech2Text service
https://github.com/emibcn/podcast2text
deepsource docker docker-compose google-speech google-speech-to-text hacktoberfest javascript poc
Last synced: 3 months ago
JSON representation
Proof of concept for transcribing podcasts into text using GCP Speech2Text service
- Host: GitHub
- URL: https://github.com/emibcn/podcast2text
- Owner: emibcn
- License: gpl-3.0
- Created: 2019-04-14T14:01:37.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2022-06-27T07:51:45.000Z (almost 3 years ago)
- Last Synced: 2025-01-13T17:34:02.925Z (4 months ago)
- Topics: deepsource, docker, docker-compose, google-speech, google-speech-to-text, hacktoberfest, javascript, poc
- Language: JavaScript
- Homepage:
- Size: 82 KB
- Stars: 2
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[](https://deepsource.io/gh/emibcn/Podcast2Text/?ref=repository-badge)
Proof of Concept for transcoding podcasts into text using GCP Speech2Text service, following its [NODE JS tutorial](https://cloud.google.com/speech-to-text/docs/quickstart-client-libraries).
# Installation
1. Download this repo:
```shell
git clone https://github.com/emibcn/Podcast2Text.git
```
2. Change directory into it:
```shell
cd Podcast2Text
```
3. Create local directories:
```shell
mkdir flac credentials
```
4. Create GCP credentials for consuming Speech2Text service at [GCP IAM](https://console.cloud.google.com/iam-admin/iam) with -at least- `Service Usage Consumer` permission.
5. Copy credentials file to `./credentials` directory
6. Create `.env` file with `GOOGLE_APPLICATION_CREDENTIALS=[CREDENTIALS FILENAME]` (without directory)
# Usage
There is a script helper to transcode any audio file into text. It's syntax is:
```shell
./transcode.sh [START]
```
- `FILEPATH`: Path (relative or absolute) to podcast audio file
- `START`: Initial start seek (transcode beginning at this position). Same syntax as FFMPEG `-ss` option.
This will encode the supplied file to FLAC format into `./flac` directory and then use the encoded file to send it to GCP Speech2Text service and get its transcription printed on screen.