Model reference · open weights
IndexTTS-2.5 is an open-weight audio or speech model from IndexTeam, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
IndexTTS-2.5 IndexTTS-2.5 is a zero-shot text-to-speech model that clones a voice from a single reference audio clip. It supports Chinese, English, Japanese, Spanish and Arabic, with cross-lingual voice transfer and emotion control disentangled from timbre. Compared with IndexTTS-2, it adds Japanese, Spanish and Arabic, infers faster, adds speaking speed control, and improves controllability of Chinese Pinyin, English CMU phonemes and Japanese Kana. Model Details - Developed by: IndexTeam, Bilibili - Model type: Autoregressive zero-shot TTS — GPT backbone, flow-matching speech-to-mel decoder, BigVGAN vocoder - Parameters: ~0.8B (GPT backbone) - Languages: Chinese, English, Japanese, Spanish, Arabic - Output: 22.05 kHz waveform - License: bilibili Model Use License Agreement - Repository: github.com/index-tts/index-tts - Paper: arXiv:2601.03888 Getting Started Requires Python 3.10–3.11, an NVIDIA GPU, and roughly 6 GB of VRAM for inference. Install Download the weights Auxiliary models (w2v-bert-2.0, MaskGCT semantic codec, CAMPPlus, BigVGAN) are not part of this repository; they are downloaded into checkpoints/hfcache/ on first run. Inference Web UI Limitations - Long text is split into segments and the pieces are concatenated with a short silence, so prosody is not modelled across a segment boundary. - Emotion control from a text description needs the QwenEmotion model, which is loaded only when IndexTTS2 is constructed with useqwenemo=True. Passing useemotext=True without it raises at inference time. - Enabling random sampling for emotion (userandom=True) reduces voice cloning fidelity. - The model does not verify that the speaker in a reference clip consented to being cloned. Obtaining that consent is the user's responsibility, and all use is subject to the license terms. Citation
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | IndexTeam |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | indextts |
| Released | 2026-08-10 |
| Popularity | 11k downloads / month |
| Likes | 192 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| IndexTTS-2.5 | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys indextts-2-5 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (indextts-2-5 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="indextts-2-5" -F file=@audio.mp3
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗