Audio & Voice

Edit video and podcasts by editing text transcripts.

High-quality AI voice synthesis, cloning, and dubbing.

AI music generation with vocals and full songs.

AI music generation for songs and instrumentals.

Speech-to-text model family widely used for transcription.

AI meeting notes and transcription.

Studio-quality AI voiceovers for videos and courses.

Text-to-speech reader for documents and web pages.

AI noise cancellation for calls and recordings.

AI meeting recorder, transcription, and summaries.

Model hub, Spaces, and inference for open ML.

Run open AI models via API without managing GPUs.

Fast generative media APIs for images, video, and audio.

Google AI notebooks grounded in your uploaded sources.

AI meeting recorder for Zoom/Meet/Teams.

Korean-first AI voice acting and TTS for creators.

High-quality AI voice cloning and TTS from a Korean AI lab.

Korean speech recognition API for meetings and calls.

Korean audio AI for sound recognition APIs.

Naver CLOVA meeting transcription with strong Korean ASR.

All-in-one AI media editor popular in Asia for audio/video cleanup.

Text to video with stock + TTS for social.

Remote studio recording with AI clips and transcription.

Ultra-realistic TTS voices for creators.

AI composer for soundtracks and classical-leaning scores.

Instant AI tracks you can release.

Free AI meeting recorder with great summaries.

Voice-to-text dictation that turns speech into clean writing across apps.