bananamind tts needs about 0.5 GB of memory at Q8_0 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.0 GB (Q8_0) to 0.1 GB (F32).
BananaMind TTS V2.1 – lightweight fixed‑voice text‑to‑speech
BananaMind TTS V2.1 is a 13M parameter Tacotron‑lite model with a HiFi‑GAN vocoder. It supports English (en‑us) and German (de‑de) locales. The model is character‑based and outputs 22050 Hz mono audio.
Good at
- Fixed‑voice TTS
- Low‑parameter footprint
- Character‑based tokenizer
Limits
- No voice cloning or speaker embeddings
- German umlauts only in de‑de tokenizer
- Numbers best written as words
Best for
- Embedded TTS devices
- Low‑memory inference
- Simple voice prompts
Who it’s for. Developers needing a small, fixed‑voice TTS solution for English or German. The model is ideal for applications where voice consistency and low resource usage are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| F32 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F32 | 0.1 GB | 0.6 GB | Fits | Get file → |
For most use cases, Q8_0 is recommended. The Q8_0 file is 0.04 GB and requires about 0.5 GB of VRAM at 8 k context. F32 versions are 0.05 GB and need about 0.6 GB of VRAM. Memory estimates are approximate.
What GPU do you need for bananamind tts?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is F32 (0.1 GB file, about 0.6 GB in use).
Which bananamind tts quant should you choose?
Q8_0 (0.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q8_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about bananamind tts
How much VRAM does bananamind tts need?
About 0.5 GB at Q8_0 with an 8K context window. That is the 0.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run bananamind tts on an 8 GB GPU?
Yes, with F32: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bananamind tts GGUF?
It depends on the quant: Q8_0 is 0.0 GB, Q8_0 is 0.0 GB, F32 is 0.1 GB, F32 is 0.1 GB.
Where can I download bananamind tts GGUF?
The files are on Hugging Face in the cstr/bananamind-tts-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does bananamind tts use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run BananaMind TTS V2.1 on 1 GB VRAM?
The Q8_0 quantized model requires about 0.5 GB of VRAM at 8 k context, so 1 GB VRAM is sufficient.
Does the model support voice cloning?
No, the model provides fixed voices only and does not support speaker embeddings or reference audio conditioning.
What languages are supported?
English (en‑us) and German (de‑de) locales are available; other languages are not supported.