ElevenLabs, hailed as the leading AI voice company, has recently introduced a speech recognition model called scribe_v1. This model supports the transcription of audio into text for an impressive 99 languages.

What's more, the free tier is quite generous, allowing you to upload audio or video files up to 1GB in size per submission.

Using it in Video Translation Software

1. Upgrade your software to version v3.59+

2. Go to this page and create an API key: https://elevenlabs.io/app/settings/api-keys

3. In the video translation software, go to Menu -- TTS Settings -- Elevenlabs.io and enter the API key you copied, then save.

4. Select Elevenlabs.io in the speech recognition channel to start using it.

Using it on the Web

1. Go to the webpage https://elevenlabs.io/app/speech-to-text. If you don't have an account, please register with your email. No phone verification, card binding, or recharge is required.
2. After logging in, click Speech to text on the left side, as shown in the picture below.

3. After the transcription is complete, click on the displayed name to enter the transcription results page.