A user calls the suite state of the art in voice AI.
A user highlights a suite of tiny text-to-speech models that they describe as open source, on-device and state of the art.
21.4K
9 Sources, first seen ago
@GradiumAIA new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. https://gradium.ai/phonon🧵
@mattturckBig news in *open source* voice AI: a suite of tiny text-to-speech, on-device SOTA models 🔥🔥🔥
@timshi_ailow latency voice models should be on device, always on@GradiumAIA new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. https://gradium.ai/phonon🧵@mattturckBig news in *open source* voice AI: a suite of tiny text-to-speech, on-device SOTA models 🔥🔥🔥@timshi_ailow latency voice models should be on device, always on@GradiumAIA new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. https://gradium.ai/phonon🧵@mattturckBig news in *open source* voice AI: a suite of tiny text-to-speech, on-device SOTA models 🔥🔥🔥@timshi_ailow latency voice models should be on device, always on@GradiumAIA new frontier for on-device speech. We're open-sourcing Phonon, a suite of TTS models under 50m parameters, setting a new standard for naturalness and accuracy across languages, with the broadest inference support to date. Phonon-31m is available under Apache 2.0. https://gradium.ai/phonon🧵@mattturckBig news in *open source* voice AI: a suite of tiny text-to-speech, on-device SOTA models 🔥🔥🔥@timshi_ailow latency voice models should be on device, always on—
Not ranked yet
—
Not ranked yet
Comments