ElevenLabs, known as the world's top AI voice company, recently launched a speech recognition model called scribe_v1, which supports transcribing audio into text for 99 languages.

Moreover, it offers a generous free quota, allowing uploads of audio or video files up to 1GB per use.

Using in Video Translation Software

1. Upgrade the software to version v3.59 or higher.
2. Go to this page to create an API key: https://elevenlabs.io/app/settings/api-keys
   
3. In the video translation software, navigate to Menu → TTS Settings → Elevenlabs.io, paste your copied API key, and save it.
   
4. Select Elevenlabs.io as the speech recognition channel to start using it.
   

Using on the Web

1. Visit the webpage https://elevenlabs.io/app/speech-to-text. If you don't have an account, sign up with your email—no phone verification, card binding, or top-up required.
2. After logging in, click Speech to text on the left side and follow the steps as shown below.
   
3. Wait for the transcription to complete, then click on the displayed name to access the transcription results page.