Languages & Translation | MeetStream Docs

Meetings aren’t English-only, and neither is the transcription stack. Language handling is a per-provider setting under recording_config.transcript.provider.

Language options by provider

Provider	Field	Default	Notes
Deepgram	`language`	`en`	Set explicitly, or `detect_language: true` for auto-detection
AssemblyAI	`language_code`	`en_us`
Sarvam	`language_code`	`en-IN`	Strongest choice for Indic languages
MeetStream engine	`language`	`auto`	Detects automatically by default
JigsawStack	`language`	`auto`	Detects automatically; supports 162 documented languages
Deepgram Streaming	`language`	`en`	Live transcripts

Each provider expects its own language-code format (en vs en_us vs en-IN) — the CLI’s -l/--language flag passes your value through unchanged.

MeetStream does not impose one global language list. Support follows the transcription provider you select. For JigsawStack, use auto or one of its 163 codes for 162 supported languages, sourced from the JigsawStack language reference.

Translation

Two providers can translate while transcribing:

Sarvam: set "mode": "translate" (instead of the default transcribe) — built for Indic-language meetings that need English output.
MeetStream engine and JigsawStack: set "translate": true alongside auto language detection.

{
  "recording_config": {
    "transcript": {
      "provider": { "sarvam": { "mode": "translate", "language_code": "hi-IN" } }
    }
  }
}

Mixed-language meetings

For meetings that switch languages mid-call, prefer a provider with auto-detection (meetstream or jigsawstack) — and remember you can re-transcribe any recording with a different provider or language after the fact, without re-recording anything:

meetstream transcribe <bot-id> -p sarvam -l hi-IN