Sarvam Dubbing API Verified
Key insights
Concrete technical or product signals.
- One job can target several languages and produce every requested export format. Video formats include MP4, MOV, MKV, WebM, AVI, FLV, and WMV. Audio formats include WAV, MP3, and M4A.
- Starter allows 2 GB and 1 hour. Pro allows 3 GB and 1 hour. Business allows 4 GB and 4 hours. The file must contain at least one second of audible speech.
- editor_flow true is for the Creator Studio editor. It suppresses auto-export and costs more than the default API path.
Use cases
Where this shines in production.
- Indic video localization
- Speaker-preserving dubs
- Subtitle and audio exports from one job
Limitations & trade-offs
What to watch for.
- The upload URL is short-lived and must not receive the API key. A completed job can still be rendering exports.
- Enterprise file limits are not on the public overview. Sarvam says to check them with the account team.
Models referenced
Declared model dependencies or integrations.
Sarvam dubbing, Sarvam voice cloning
Related prompts
Hand-picked or latest prompt templates.
Prompt
Prompt-injection resistant assistant
System prompt that treats retrieved docs, tickets, and web pages as untrusted data. Use in multi-tenant RAG and browsing agents. This is a defensive template, not an attack or bypass playbook.
Prompt
Computer-use agent with approval gates
System prompt for browser/desktop agents (Grok Bot, computer-use tools). Allows research and drafts, but pauses before send, purchase, delete, or production changes. Not a jailbreak or bypass guide.
Prompt
Transcript to summary and action items
Turn a speech transcript into decisions, owners, and follow-ups. Use after Gemini 3.5 Transcribe, Whisper, or MAI-Transcribe. Do not use on raw audio; transcribe first.
Prompt
Product image generation prompt
A reusable image prompt for catalog and hero shots: subject, lighting, lens, negative constraints, and text-in-image rules. Works with Firefly, Midjourney, MAI-Image, Qwen-Image, and SDXL. Not for photorealistic people or brand-logo cloning.
Prompt
LLM output evaluation rubric
Judge a model answer against a task, retrieved evidence, and pass/fail thresholds. Use for golden-set grading and regression evals. Not a substitute for human review on high-risk decisions.
Prompt
Strict JSON extraction prompt
Extract structured fields into JSON that matches a schema. Pair with provider structured-output / JSON-schema modes when available. Do not use when the output is meant to be prose.
Looking for a tighter match? Search the prompt library.
Sarvam Dubbing API FAQ
What is Sarvam Dubbing API?
The Sarvam Dubbing API localizes video and audio into 12 Indian languages in one asynchronous job, with optional speaker voice cloning, translation tone control, and exports of dubbed video, isolated audio, and SRT subtitles. It is the programmatic side of Content Studio. A job is created with POST /jobs, the file is uploaded to a signed URL, then started and polled. Sarvam's September 26, 2026 changelog marks the API as available. On the Starter plan the default rate is ₹40 per minute of source media when editor_flow is false, multiplied by the number of target languages.
When should teams use Sarvam Dubbing API?
Indic video localization
What should teams watch out for with Sarvam Dubbing API?
The upload URL is short-lived and must not receive the API key. A completed job can still be rendering exports.
Related
Comparisons, platforms, and models teams often view next.