The artificial intelligence voice company ElevenLabs, known as the strongest on Earth, recently launched a speech recognition model scribe_v1, which supports transcribing audio into text in 99 languages.

Moreover, the free quota is quite high, supporting uploading 1G of audio or video files at a time.

Using it in the video translation software pyVideoTrans This article introduces two ways to use it, including online web use.

Using it in Video Translation Software

1. Upgrade to version v0.59 https://pvt9.com/downpackage

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

3. Fill in the API key you copied in the video translation software Menu--TTS Settings--Elevenlabs.io, and then save it

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

Using it on the Webpage

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

3. After waiting for the transcription to complete, click the displayed name to enter the transcription result page.