vllm-project/vllm-omni

[New Model] Add TADA (Hume AI) TTS model support

Open

#2001 aperta il 19 mar 2026

Vedi su GitHub
 (8 commenti) (0 reazioni) (1 assegnatario)Python (1067 fork)github user discovery
good first issuehelp wantednew model

Metriche repository

Star
 (4990 star)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

Model

TADA by Hume AI — a speech-language model that unifies speech synthesis with text generation using 1:1 text-speech token alignment built on Llama 3.2.

Architecture

  • Encoder (HumeAI/tada-codec): encodes reference audio into aligned token sequences
  • LLM (TadaForCausalLM): autoregressive generation, available in 1B and 3B-ML (multilingual) variants
  • Generates the complete speech segment per text token in a single AR step (dynamic duration/prosody)

This would likely be a 2-stage pipeline in vllm-omni (AR generation → codec decode), similar to Qwen3 TTS / Fish Speech.

References

cc @ashok-arora — would you be interested in taking a look at this?

Guida contributor