AI Speech Text

Before getting started

• Learn how to create a VNG Cloud account

• Learn how to login into AI Speech Text portal

Create Speech-to-Text Transcription

Speech-to-Text (STT) transcription is a technology that converts spoken language into written text. It's like having a real-time transcriptionist, capturing every word you say.

Step-by-Step Guide to Speech-to-Text Transcription

1. Access to the Speech-to-Text Portal: https://ai-speech-text.console.vngcloud.vn/stt

2. Upload Your Audio File:

   • Select the audio file you want to transcribe from your device.

   • Ensure the audio file format is supported (e.g., MP3, WAV, etc.).

3. Select Audio Encoding Type:

   • Choose the correct encoding type for your audio file. This information is often available in the file properties or metadata. Common encoding types include MP3 and WAV.

4. Select Language:

   • Choose "Vietnamese" as the language for the transcription. This will help the system accurately recognize and transcribe the spoken language.

5. Start the Transcription Process:

   • Click the "Turn speech to text" button to initiate transcription.

6. Review and Edit the Transcription:

   • Once the transcription is complete, review the generated text for accuracy.

   • Edit and correct any errors or inaccuracies as needed.

Create Text-to-Speech Transcription

Text-to-Speech (TTS) transcription is a technology that converts written text into spoken language. It's like having a computer read text aloud, making it accessible to a wider audience and streamlining content consumption.

Step-by-Step Guide to Text-to-Speech Transcription:

1. Access to the Text-to-Speech Portal: https://ai-speech-text.console.vngcloud.vn/tts

2. Select the Text-to-Speech Engine:

   • Choose the "Standard Mode" engine for general-purpose text-to-speech.

3. Input or Upload Your Text:

   • Direct Input: Type your text directly into the text box provided.

   • File Upload: Upload a text file containing the text you want to convert.

4. Select the Language:

   • Choose "Vietnamese" as the language for the synthesized speech.

5. Customize the Audio Voice:

   • Select the desired voice from the available options. You can choose between male and female voices, and adjust the voice's tone and speed.

6. Adjust Audio Speed and Encoding:

   • Audio Speed: Set the desired speed of the synthesized speech.

   • Audio Encoding: Choose the appropriate audio format (e.g., MP3, WAV) and encoding settings.

7. Start the Transcription Process:

   • Click the "Turn text to speech" button to initiate the text-to-speech process.

8. Download the Audio File:

   • Once the process is complete, download the generated audio file.

Pricing Model

For the initial phase, we offer a free tier to attract users and encourage experimentation. This tier can have limitations, such as a certain number of free minutes or characters per month.

Once users exceed the free tier limits, they can then upgrade to a paid plan. This approach allows users to experience the value of the service before committing to a paid subscription.

For Speech-to-Text:

• Per-Minute Pricing: Charge a fixed rate per minute of audio processed.

For Text-to-Speech:

• Per-Character Pricing: Charge a fixed rate per character processed.