Model reference · open weights
Inflect-Nano is an open-weight audio or speech model from owensong. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | owensong |
|---|---|
| Type | Audio & music |
| Task | Text→speech |
| Released | 2026-06-25 |
| Popularity | 593 downloads / month |
| Licence | Open weights |
About
Fixed-voice English TTS with deterministic seeds, long-text handling, and CPU or CUDA inference.
A note from Owen
Thanks so much for all the support shown on this project! I built and funded Inflect v2 independently - if this release finds a real audience, I would like to continue the project with a v3, which might include things like more langauges, voices, and stability improvements. If the model is useful to you, leaving a like on Hugging Face genuinely helps more people discover it.
New: public adaptation toolkit
Prepare data, audit train/validation splits, adapt a fixed voice or language, resume training, evaluate checkpoints, and export PyTorch or ONNX packages with the Inflect adaptation toolkit. Adapted quality is experimental and depends on the dataset, frontend, and fluent-speaker evaluation.
Inflect v2 uses one public API across two sizes: Micro prioritizes quality below 10M parameters; Nano prioritizes footprint below 4M.
These are held-out text generations, not reconstructions of training audio. Each transcript is shown exactly as passed to the public frontend.
| Test | Exact transcript | Generated audio |
|---|---|---|
| Conversational | It wasn't until later that I realized what had actually happened. | |
| Punctuation | First, close the window; second, turn off the lamp; finally, lock the door. | |
| Numbers | The package weighs twelve point six kilograms and arrived on July twenty-first. | |
| Names and places | Gwendolyn photographed the eucalyptus trees outside Ljubljana. | |
| Technical | The system runs on three core components that all have to stay in sync. |
No single metric captures TTS quality. Inflect v2 reports human preference, predicted naturalness, multi-ASR intelligibility, complete footprint, and runtime separately rather than compressing them into one unverifiable score.
| Community preference ↑ | UTMOS22 ↑ | Two-ASR semantic WER ↓ | Complete FP32 weights ↓ | 4-thread CPU throughput ↑ |
|---|---|---|---|---|
| 63.9% | 4.386 | 4.21% | 15.97 MB | 10.72× real-time |
The headline row always refers to Inflect-Nano-v2. Detailed competitor results and protocol boundaries are kept visible below.
Comparison set. Results include KittenTTS Nano, Piper Low, and Supertonic 3, established compact or local TTS baselines with larger deployable weight footprints than both Inflect releases. Weight sizes are compared at package level, and no single metric is treated as proof of overall superiority.
Inflect-Nano-v2 recorded a 63.9% preference rate (22 wins · 12 losses · 2 ties) in the final anonymous community study. Systems were hidden, left/right order was randomized, and ties count as half a win. This is descriptive community evidence, not formal MOS.
The UTMOS22 run used 500 identical unseen prompts per voice. KittenTTS and Piper are equal-weight two-voice means; their observed voice ranges appear as whiskers. Supertonic 3-step is reported below the plotted range rather than flattening every other system.
Inflect-Nano-v2: 4.386 UTMOS22, 95% bootstrap CI 4.372–4.399. UTMOS22 is a learned predictor, not human MOS.
The headline score is the equal-weight mean of Qwen3-ASR and Nemotron 3.5 corpus WER for every system. Whisper is excluded consistently from the headline because it produced insertion-heavy hallucinations on a subset of otherwise intelligible Supertonic 8-step clips. It is not deleted: the complete three-ASR evidence remains below.
| System / voice | Qwen3-ASR ↓ | Nemotron 3.5 ↓ | Whisper large-v3 ↓ |
|---|---|---|---|
| Inflect-Micro-v2 | 2.52% | 5.45% | 2.73% |
| Inflect-Nano-v2 | 2.79% | 5.63% | 2.65% |
| KittenTTS Nano · Bruno | 2.15% | 3.96% | 2.17% |
| KittenTTS Nano · Hugo | 2.39% | 3.80% | 2.11% |
| Piper Low · Danny | 2.62% | 5.60% | 2.55% |
| Piper Low · Ryan | 2.81% | 5.51% | 2.87% |
| Supertonic 3 · M2 · 3-step | 3.03% | 6.04% | 3.22% |
| Supertonic 3 · M2 · 8-step | 2.05% | 3.56% | 8.08% |
For Inflect-Nano-v2, the individual results are 2.79% Qwen3-ASR, 5.63% Nemotron 3.5, and 2.65% Whisper large-v3. The former three-model mean, 3.69%, is retained only as a descriptive audit value and is not used as the headline score.
These views are diagnostics, not additional leaderboards. They show where the recognizers disagree and which prompt categories still produce recoverable transcription errors.
Both Inflect releases synthesize comfortably faster than real time on CPU. The managed reference run used a Hugging Face CPU Upgrade instance (8 vCPU, 32 GB RA
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys inflect-nano for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (inflect-nano 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="inflect-nano" -F file=@audio.mp3
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.