Model reference · open weights
gepard-1.0 is an open-weight audio or speech model from nineninesix, 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
[](https://discord.gg/NzP3rjB4SB) [](https://opensource.org/licenses/Apache-2.0) [](https://huggingface.co/nineninesix/gepard-1.0/resolve/main/gepardtechreport.pdf) [](https://www.nineninesix.ai/) [](https://huggingface.co/spaces/nineninesix/gepard) [!IMPORTANT] 2026-08-06 — updated stophead weights. Every other parameter is unchanged. This fixes premature stopping: multi-sentence inputs are now carried through to the end instead of cutting off at the first sentence boundary, and the effective duration ceiling is lifted. Short-phrase behaviour is unaffected. GEnerative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue Gepard is a text-to-speech model built for real-time conversation. It starts speaking the moment text begins arriving, generating audio piece by piece instead of waiting for a full sentence — so it feels like a live voice, not a recording. It's a single language model that learned text and speech together, so the output carries natural rhythm and timing rather than the flat, stitched tone of older pipelines. The name evokes "Gepard"(/geh-PART/), German for cheetah — a nod to the model's low-latency, high-throughput streaming. Want to use Gepard in production without hosting it yourself? You can skip the deployment and use our real-time TTS API — a fully managed, Cartesia-compatible service with millisecond time-to-first-chunk, voice cloning, and streaming built in. If you've used Cartesia, you already know how to use it: point the base URL at https://api.nineninesix.ai and the official Cartesia SDKs just work. Roughly 22 hours of audio for $5, and free credits to start (no credit card required). Try the live demo or grab an API key. Highlights: - One clean pass per frame — the whole audio frame (32 orthogonal FSQ channels) is sampled in one step, no depth-transformer. - Extra quality, for free: CFG refinement (normally a two-pass cost) is baked into the weights, with the two-pass mode still available as a quality dial. - Real-time on vLLM: ~25× real time on a single RTX 5090, with first audio chunk (TTFA) in ~50 ms - Scales to many callers: One 96GB GPU (RTX Pro 6000 Blackwell) holds up to 256 conversations in parallel. - Vo
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | nineninesix |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 556M |
| Variants | 1 |
| Runs with | transformers |
| Based on | nineninesix/qwen3_5-full-attn-only-14 |
| Released | 2026-06-22 |
| Popularity | 50k downloads / month |
| Likes | 131 |
| Licence | Open weights |
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 |
|---|---|---|---|---|---|
| gepard-1.0 | 556M | BF16 | ~1.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys gepard-1-0 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (gepard-1-0 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="gepard-1-0" -F file=@audio.mp3
Details
Languages
Trained / evaluated on
Tags
Papers
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗