Model Detail

IndexTTS-2 is an audio model released by IndexTeam. The model is registered under the text-to-speech pipeline tag on Hugging Face.

IndexTTS-2 is published on Hugging Face but our pipeline has not yet captured architecture, license, or parameter-count metadata for this entry. The data is refreshed daily, so these fields typically populate within 24–48 hours of release.

IndexTTS-2 is best fit for speech recognition, transcription, or speech synthesis depending on the task head. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.