@nate_512Fishaudio's s2.1 pro is an open-weight tts model that's 2x faster than cartesia and costs 1/6th of elevenlabs. 56.3 chars/s throughput, 83+ languages, ~90ms latency, on-prem with zero data retention. elevenlabs had no real open-source competition until now

@nate_512Fishaudio's s2.1 pro is an open-weight tts model that's 2x faster than cartesia and costs 1/6th of elevenlabs. 56.3 chars/s throughput, 83+ languages, ~90ms latency, on-prem with zero data retention. elevenlabs had no real open-source competition until now