Search results

Open-source project that uses AI for speech, voice, transcription, music, or other audio workflows.

Open-source project that uses AI for speech, voice, transcription, music, or other audio workflows.

Kokoro TTS uses AI for speech, voice, transcription, music, or other audio workflows.

Kyutai TTS uses AI for speech, voice, transcription, music, or other audio workflows.

Works with speech, voice, music or other audio using machine-learning models.

LazyPy uses AI for speech, voice, transcription, music, or other audio workflows.

Letterfork uses AI for speech, voice, transcription, music, or other audio workflows.

LOVO uses AI for speech, voice, transcription, music, or other audio workflows.

Mazmazika uses AI for speech, voice, transcription, music, or other audio workflows.

MMAudio uses AI for speech, voice, transcription, music, or other audio workflows.

Moe TTS uses AI for speech, voice, transcription, music, or other audio workflows.

Mubert uses AI for speech, voice, transcription, music, or other audio workflows.

Works with speech, voice, music or other audio using machine-learning models.

Murf AI uses AI for speech, voice, transcription, music, or other audio workflows.

MuseGen uses AI for speech, voice, transcription, music, or other audio workflows.

MusicFX uses AI for speech, voice, transcription, music, or other audio workflows.

MusicGen uses AI for speech, voice, transcription, music, or other audio workflows.

Open-source project that uses AI for speech, voice, transcription, music, or other audio workflows.

MusicGPT uses AI for speech, voice, transcription, music, or other audio workflows.

MVSEP uses AI for speech, voice, transcription, music, or other audio workflows.

APIs for messaging, voice, and phone verification.

Ondoku uses AI for speech, voice, transcription, music, or other audio workflows.

OpenAI.fm uses AI for speech, voice, transcription, music, or other audio workflows.

On-device voice dictation for macOS — transcribes a 5-minute clip in 2.8 s; noise-robust, paste at cursor. 99 languages, ~8 MB, no telemetry. MIT.