Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added metadata files: .clawhub/origin.json and _meta.json. - SKILL.md updated to include a metadata section with environment and usage requirements. - No changes to code or user-facing functionality.
What 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
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Convert this Hindi text to speech: 'Namaste, kaise hain aap?' using a female voice
- 1Reads SARVAM_API_KEY from environment
- 2Calls sarvam_cli.py tts with the provided text, lang hi-IN, and speaker meera
- 3Writes the audio output to hello.wav
- 4Returns the file path to the user
hello.wav audio file containing the spoken Hindi phrase
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.