Overview
The Sarvam AI API Tools Suite is a collection of Python command-line tools for interacting with Sarvam AI APIs. The suite currently includes five tools: speech-to-text audio transcription with speaker diarization, automated image renaming with metadata catalog generation, text translation across Indic languages and English, text-to-speech voice synthesis, and document OCR and parsing. Each tool runs standalone, handles API rate limits with polite request cooldowns and backoff, and shares a single API key configuration. An interactive Gradio web front end (app.py) is also included so you can interactively test the Speech-to-Text, Translation, Text-to-Speech, and Document OCR tools directly from your browser.
The tools are designed for batch processing and include features such as resumable caches, MD5 deduplication, and rate-limit protection. For example, the speech transcription tool supports multiple output modes, speaker diarization, and cost-optimization options like audio trimming and silence removal. The image renamer uses Sarvam AI's Document Intelligence API to analyze scene content and generate descriptive filenames. The translation tool supports 23 languages, and the TTS tool offers 44 selectable speaker personas. The document OCR tool digitizes PDFs and images into Markdown, HTML, or text with table parsing.
Installation requires Python 3.10 or higher and an active Sarvam AI API subscription key. The API key can be provided via command-line flag, environment variable, or .env file. The suite is open-source and available on GitHub.
Pricing
Free
Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.
Visit WebsitePrices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.
Use Cases
- Teams use the speech transcription tool to transcribe audio files with speaker diarization and generate formatted transcripts.
- Users use the image renamer to scan directories recursively and generate descriptive filenames based on scene content.
- Translators use the translation tool to batch translate text across 23 languages with auto source detection.
- Content creators use the TTS tool to synthesize voice with selectable speaker personas and pronunciation dictionaries.
- Organizations use the document OCR tool to digitize PDFs and images into Markdown, HTML, or text with table parsing.
- Developers use the Gradio web front end to interactively test the Speech-to-Text, Translation, Text-to-Speech, and Document OCR tools from a browser.
Features
Transcribes audio into text
Identifies speakers during transcription
Processes documents with AI
Analyzes images using computer vision
Automates SEO cataloging tasks
Provides modular Python CLI tools
Reviews
No reviews yet. Be the first to share your experience!