Speech Recognition and Translation

Transcribe mp3s, WhatsApp voice, YouTube videos in 1000+ langs with Meta’s MMS /Seemless M4T, OpenAI's GPT4o Audio LLM, Whisper v2/v3, Azure, Google, GhanaNLP, AI4Bharat & Bhasini ASR models. Optionally translate to any language too.


🎙️ Audio Files
Loading...

  Filter by Language

Choose a model and language to translate recognized audio


Run cost = 2 credits (1 credit for 12.5 words ≈ 0.08 per word)

By submitting, you agree to Gooey.AI's terms & privacy policy.

Transcription

Generated in 15.6s on 

...

Related Workflows