
Canopy Labs/Orpheus TTS
An incredibly lifelike speech synthesis model by Canopy Labs.
Orpheus v1 is Canopy Labs newest model and successor to Orpheus TTS. Check it out here.
Orpheus TTS must generate ~83 tokens/second for real-time streaming. This implementation supports streaming and, on an H100 MIG GPU, can produce:
16 concurrent real-time streams with variable traffic
24 concurrent real-time streams with consistent traffic
128 concurrent non-real-time generations for cost-efficient batching