ElevenLabs, hailed as the best AI voice company globally, recently introduced a speech recognition model, scribe_v1, capable of transcribing audio into text across 99 languages.
It also offers a generous free tier, supporting uploads of audio or video files up to 1GB in size per instance.
Using with pyVideoTrans video translation software This article describes two usage methods: online web use.
Using in Video Translation Software
Upgrade to version v0.59: https://pvt9.com/downpackage
Go to this page to create an API key: https://elevenlabs.io/app/settings/api-keys
In the video translation software, go to Menu--TTS Settings--Elevenlabs.io and enter the API key you copied, then save it.
Select Elevenlabs.io in the speech recognition channel to use it.
Using on the Web
- Go to this 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.
- After logging in, click Speech to text on the left, as shown in the figure below.
- After the transcription is complete, click the displayed name to enter the transcription result page.
