Spaces:
Running
Running
[Model Addition Request] Lightning v3.1 - Smallest AI TTS
#34
by
stalwartcoder - opened
Hi @Pendrokar ! 👋
We'd like to request the addition of Lightning v3.1 to the TTS Spaces Arena.
HuggingFace Space
Space URL: https://huggingface.co/spaces/smallestai/smallest-ai-tts-lightningv3.1-demo
Model Overview
Lightning v3.1 is a high-fidelity text-to-speech model delivering natural, expressive speech at 44 kHz native sample rate.
| Specification | Value |
|---|---|
| Model | Lightning v3.1 |
| Developer | Smallest AI |
| Native Sample Rate | 44,100 Hz |
| Supported Sample Rates | 8,000 / 16,000 / 24,000 / 44,100 Hz |
| Languages | English, Hindi, Tamil, Spanish |
| Voices | 40+ unique voices |
Gradio API
The Space has Gradio API enabled and can be called via gradio_client:
from gradio_client import Client
client = Client("smallestai/smallest-ai-tts-lightningv3.1-demo")
result = client.predict(
"Hello, this is Lightning v3.1 from Smallest AI.", # text
"Sophia (Female, American)", # voice (dropdown value)
"English", # language (dropdown value)
1.0, # speed
api_name="/synthesize_speech"
)
# result = audio file path
API Endpoint Details
| Detail | Value |
|---|---|
| API Name | /synthesize_speech |
| Audio Output Index | 0 |
| Output Format | Audio file (WAV) |
Suggested config for AVAILABLE_MODELS:
'smallestai/smallest-ai-tts-lightningv3.1-demo': '/synthesize_speech#0'
Links
- Space: https://huggingface.co/spaces/smallestai/smallest-ai-tts-lightningv3.1-demo
- Documentation: https://waves-docs.smallest.ai
- Website: https://smallest.ai
Contact
- HuggingFace: @stalwartcoder
- Email: abhishek [at] smallest [dot] ai
Let me know if you need any changes to the Space configuration or have questions about the API!
Thanks!
Pendrokar changed discussion status to
closed