Text-to-Speech
ONNX
GGUF
tts
speech
audio
indic
multilingual
int8
quantization
edge-ai
vocos
llama-3.2
indic-speak
Instructions to use adidsh/indic-speak-int8-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use adidsh/indic-speak-int8-onnx with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf adidsh/indic-speak-int8-onnx:Q5_K_M # Run inference directly in the terminal: llama cli -hf adidsh/indic-speak-int8-onnx:Q5_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf adidsh/indic-speak-int8-onnx:Q5_K_M # Run inference directly in the terminal: llama cli -hf adidsh/indic-speak-int8-onnx:Q5_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf adidsh/indic-speak-int8-onnx:Q5_K_M # Run inference directly in the terminal: ./llama-cli -hf adidsh/indic-speak-int8-onnx:Q5_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf adidsh/indic-speak-int8-onnx:Q5_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf adidsh/indic-speak-int8-onnx:Q5_K_M
Use Docker
docker model run hf.co/adidsh/indic-speak-int8-onnx:Q5_K_M
- LM Studio
- Jan
- Ollama
How to use adidsh/indic-speak-int8-onnx with Ollama:
ollama run hf.co/adidsh/indic-speak-int8-onnx:Q5_K_M
- Unsloth Desktop
- Docker Model Runner
How to use adidsh/indic-speak-int8-onnx with Docker Model Runner:
docker model run hf.co/adidsh/indic-speak-int8-onnx:Q5_K_M
- Lemonade
How to use adidsh/indic-speak-int8-onnx with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull adidsh/indic-speak-int8-onnx:Q5_K_M
Run and chat with the model
lemonade run user.indic-speak-int8-onnx-Q5_K_M
List all available models
lemonade list
- Atomic Chat
Upload LICENSE_DEED.md
Browse files- LICENSE_DEED.md +75 -0
LICENSE_DEED.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Indic Open License Deed
|
| 2 |
+
|
| 3 |
+
*A plain-language guide to the Indic Open Model License covering Bodhan AI's speech, OCR, translation, and transliteration models.*
|
| 4 |
+
|
| 5 |
+
Broad, no-cost access for research, government, nonprofit, and commercial use β with a few conditions attached.
|
| 6 |
+
|
| 7 |
+
> **This deed is a human-readable summary of the license, not a substitute for it.** Where the two disagree, the full **Indic Open Model License** governs.
|
| 8 |
+
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
## You're free to
|
| 12 |
+
|
| 13 |
+
No cost, no royalty, worldwide β for research, government, nonprofit, and commercial use, at any scale.
|
| 14 |
+
|
| 15 |
+
- β
**Run it** β for inference, in a product, in research, however you like.
|
| 16 |
+
- β
**Change it** β fine-tune, distill, quantize, merge, or otherwise build on it.
|
| 17 |
+
- β
**Self-host it** β power your own product or service with it, commercial or not.
|
| 18 |
+
- β
**Share it** β pass on copies of the model or your own version of it.
|
| 19 |
+
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
+
## As long as you
|
| 23 |
+
|
| 24 |
+
Five conditions cover almost everything. The rest of the license is these, spelled out in legal detail.
|
| 25 |
+
|
| 26 |
+
### 1. Give credit
|
| 27 |
+
|
| 28 |
+
Wherever you ship the model or a derivative to anyone else, say where it came from β and don't strip out existing notices.
|
| 29 |
+
|
| 30 |
+
```
|
| 31 |
+
"Built with [Model Name] from Bodhan AI / AI4Bharat."
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
### 2. Pass it on the same way
|
| 35 |
+
|
| 36 |
+
If you give your fine-tuned or derived version to anyone else β hand it over, or run it as a service for them β it carries this exact license. You can't relicense it on different terms.
|
| 37 |
+
|
| 38 |
+
### 3. Ask before hosting it for others
|
| 39 |
+
|
| 40 |
+
Self-hosting is free. But if you're going to run it as an API or hosted service that *other people or companies* call directly, that needs Bodhan AI's written sign-off first β unless you're a nonprofit, government, or academic user, or you publicly release an equally capable open version within 90 days.
|
| 41 |
+
|
| 42 |
+
### 4. Don't use it to cause harm
|
| 43 |
+
|
| 44 |
+
No exceptions β not even for nonprofit or research use. That means no:
|
| 45 |
+
|
| 46 |
+
- child sexual abuse material, or content that sexualizes minors
|
| 47 |
+
- weapons development, including chemical, biological, radiological, or nuclear
|
| 48 |
+
- mass surveillance or social-scoring systems
|
| 49 |
+
- disinformation campaigns, including election manipulation
|
| 50 |
+
- automated decisions that affect someone's legal rights without human oversight
|
| 51 |
+
- deepfakes or voice clones of real people without their consent
|
| 52 |
+
- robocalls, auto-dialers, or voice-phishing scams
|
| 53 |
+
- AI companion products designed to simulate romance or foster emotional dependency
|
| 54 |
+
|
| 55 |
+
### 5. Talk to us if your product gets huge
|
| 56 |
+
|
| 57 |
+
If your own product built on this β not through hosting it for others, that's covered above β crosses either threshold, you'll need a separate commercial license. Doesn't apply to nonprofit, government, or academic users.
|
| 58 |
+
|
| 59 |
+
| Threshold | |
|
| 60 |
+
|---|---|
|
| 61 |
+
| **500M+** | monthly active users |
|
| 62 |
+
| | *or* |
|
| 63 |
+
| **$250M+** | annual revenue |
|
| 64 |
+
|
| 65 |
+
---
|
| 66 |
+
|
| 67 |
+
## Good to know
|
| 68 |
+
|
| 69 |
+
- **No warranty.** The model is provided as-is. It isn't tested or certified for safety-critical use β medical, aviation, nuclear, or similar β so test thoroughly before relying on it in high-stakes settings.
|
| 70 |
+
- **You handle your own compliance.** Export controls, sanctions, and data-protection law (including India's DPDP Act, where it applies) are on you, not Bodhan AI.
|
| 71 |
+
- **This deed doesn't replace the license.** It leaves out most of the legal detail β termination, dispute resolution, confidentiality, and more all live in the full text. Read that before you rely on anything here.
|
| 72 |
+
|
| 73 |
+
---
|
| 74 |
+
|
| 75 |
+
Indic Open Model License β Bodhan AI / AI4Bharat, IIT Madras Β· Full license at [bodhan.ai](http://bodhan.ai)
|