Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
Rather not self-host? These services do the same job out of the box.
Vbee
Voice AI
Natural Vietnamese AI voices from text, many speakers — ready to use, no model to host.
ElevenLabs
High-quality multilingual AI voices: text-to-speech, voice cloning, video dubbing.