sarvam
Communication
v1.0.1
BenignUse Sarvam AI for Indian language Text-to-Speech (TTS), Speech-to-Text (STT), Translation, and Chat.
2464 downloads464 installsby @iammhk
Setup & Installation
Install command
clawhub install iammhk/sarvamIf the CLI is not installed:
Install command
npx clawhub@latest install iammhk/sarvamOr install with OpenClaw CLI:
Install command
openclaw skills install iammhk/sarvamor paste the repo link into your assistant's chat
Install command
https://github.com/openclaw/skills/tree/main/skills/iammhk/sarvamWhat This Skill Does
Connects to Sarvam AI's API to handle Indian language text-to-speech, speech-to-text, translation, and chat. Supports multiple languages including Hindi and Bengali, with several voice options for TTS output.
Sarvam AI is purpose-built for Indian languages, covering TTS, STT, translation, and chat in a single API rather than stitching together multiple general-purpose services.
When to Use It
- Transcribing Hindi audio recordings to text
- Generating spoken Bengali announcements from a script
- Translating customer support messages between Indian languages and English
- Building a chatbot that responds in regional Indian languages
- Converting English documentation into spoken Hindi audio
View original SKILL.md file
# Sarvam AI Skill
This skill provides access to Sarvam AI's suite of Indian language models.
## Usage
### Text to Speech (TTS)
Generate speech from text in various Indian languages.
```bash
python skills/sarvam/scripts/sarvam_cli.py tts "Namaste, kaise hain aap?" --lang hi-IN --speaker meera --output hello.wav
```
**Parameters:**
- `text`: The text to speak.
- `--lang`: Language code (e.g., `hi-IN` for Hindi, `bn-IN` for Bengali, etc.).
- `--speaker`: Voice ID (e.g., `meera`, `pavithra`, `arvind`).
- `--output`: Output file path (default: `output.wav`).
### Speech to Text (STT)
Transcribe audio files.
```bash
python skills/sarvam/scripts/sarvam_cli.py stt path/to/audio.wav --model saaras:v3
```
**Parameters:**
- `file`: Path to the audio file (wav, mp3).
- `--model`: Model to use (default: `saaras:v3`).
- `--mode`: STT Mode: `transcribe` (default), `translate` (to English), `verbatim`, `translit`, `codemix`.
### Translation
Translate text between Indian languages and English.
```bash
python skills/sarvam/scripts/sarvam_cli.py translate "Hello, how are you?" --source en-IN --target hi-IN
```
**Parameters:**
- `text`: Text to translate.
- `--source`: Source language code.
- `--target`: Target language code.
### Chat
Interact with Sarvam's LLM (sarvam-2g).
```bash
python skills/sarvam/scripts/sarvam_cli.py chat "What is the capital of India?"
```
**Parameters:**
- `message`: User message.
- `--model`: Model to use (default: `sarvam-2g`).
- `--system`: Optional system prompt.
## Setup
1. **Environment Variable:**
Ensure your API key is set in `.env` (already done for this workspace):
```bash
SARVAM_API_KEY="sk_..."
```
2. **Virtual Environment:**
The skill uses a local virtual environment at `skills/sarvam/.venv`.
Dependencies (`requests`) are pre-installed here.
## Usage
Use the virtual environment's Python to run commands:
### Text to Speech (TTS)
```bash
skills/sarvam/.venv/bin/python skills/sarvam/scripts/sarvam_cli.py tts "Namaste, kaise hain aap?" --lang hi-IN --speaker meera --output hello.wav
```
### Speech to Text (STT)
```bash
skills/sarvam/.venv/bin/python skills/sarvam/scripts/sarvam_cli.py stt path/to/audio.wav --model saaras:v3
```
### Translation
```bash
skills/sarvam/.venv/bin/python skills/sarvam/scripts/sarvam_cli.py translate "Hello, how are you?" --source en-IN --target hi-IN
```
### Chat
```bash
skills/sarvam/.venv/bin/python skills/sarvam/scripts/sarvam_cli.py chat "What is the capital of India?"
```Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Transcribing Hindi audio recordings to text
AGENT
- 1Transcribing Hindi audio recordings to text
- 2Generating spoken Bengali announcements from a script
- 3Translating customer support messages between Indian languages and English
- 4Building a chatbot that responds in regional Indian languages
- 5Converting English documentation into spoken Hindi audio
OUTPUT
Use Sarvam AI for Indian language Text-to-Speech (TTS), Speech-to-Text (STT), Translation, and Chat.
Security Audits
VirusTotalBenign
OpenClawBenign
View full reportThese signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.