# Sarvam Transcribe

> Transcribes and translates Indian-language audio with Sarvam AI Saaras. Use for Hindi, Malayalam, Hinglish, and other Indic-language audio files—especially OPUS voice notes—when native-script text or English translation is needed. Does not summarize and does not call Sarvam LLMs.

- Skill: `sanjeed5/sarvam-transcribe` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add sanjeed5/sarvam-transcribe`
- Raw SKILL.md: https://api.skillmd.com/api/skills/sanjeed5/sarvam-transcribe/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- License: MIT
- Author: sanjeed5 (https://skillmd.com/u/sanjeed5)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/sanjeed5/sarvam-transcribe

---


# Sarvam Transcription

Use `scripts/transcribe.py` for voice notes up to five minutes. It calls
Sarvam's `saaras:v3` Speech-to-Text REST API and uses overlapping chunks for
audio longer than the synchronous endpoint's 30-second limit.

## Workflow

1. Confirm the requested files and preserve their chronological order.
2. A request to transcribe with Sarvam authorizes uploading only those files
   to Sarvam AI. Otherwise, tell the user that the audio will be sent to
   Sarvam before running the script.
3. Choose the output:
   - `transcribe`: normalized text in the original script (default).
   - `translate`: English translation.
   - `verbatim`: word-for-word native-script transcript.
   - `translit`: Roman-script transliteration.
   - `codemix`: Indic words in native script and English words in Latin script.
4. Use a known BCP-47 language code when reliable, such as `hi-IN` or `ml-IN`;
   otherwise use `unknown`. Always specify the language for clips under three
   seconds, where auto-detection may lack enough signal. For Hinglish, prefer
   `hi-IN --mode codemix`.
5. Run one billable pass by default:

```bash
python3 <skill-directory>/scripts/transcribe.py \
  --language hi-IN --mode transcribe "/absolute/path/to/message.opus"
```

Multiple files are supported:

```bash
python3 <skill-directory>/scripts/transcribe.py \
  --language unknown file1.opus file2.opus
```

6. Return the transcript per file. Preserve names, numbers, and uncertainty.
   Never repair unclear words by inventing details. Do not summarize unless
   the user asks separately — and never via Sarvam LLM APIs; this skill is
   speech-to-text only (`saaras:v3`).
7. When the user requests an English translation, make a second pass:

```bash
python3 <skill-directory>/scripts/transcribe.py \
  --language hi-IN --mode translate "/absolute/path/to/message.opus"
```

8. Compare names, numbers, and other identifiers across the native transcript
   and English pass. Flag every discrepancy and ask the user to verify it from
   the audio; never silently select or normalize one version. Each pass is
   separately billable.

## Authentication

The script reads `SARVAM_API_KEY`, then macOS Keychain service
`sarvam-api-key`. Never ask the user to paste the key into chat or commit it.
Never print or store the key.

If no key is configured, direct the user to create one at
https://dashboard.sarvam.ai/.

macOS Keychain (zsh):

```bash
read -s "SARVAM_API_KEY?Sarvam API key: "; echo
security add-generic-password -U -a "$USER" -s sarvam-api-key -w "$SARVAM_API_KEY"
unset SARVAM_API_KEY
```

Elsewhere:

```bash
export SARVAM_API_KEY="your-key"
```

## Scope and limits

- Requires Python 3.9+, `ffmpeg`, and `ffprobe`.
- The synchronous REST endpoint rejects audio over 30 seconds. This utility
  keeps every overlapping request below that limit.
- Supported formats: WAV, MP3, AAC, AIFF, OGG, OPUS, FLAC, MP4/M4A, AMR, WMA,
  and WebM. **Not `.oga`:** WhatsApp exporters (including `wacli media download`)
  often write voice notes as `.oga`; remux first
  (`ffmpeg -y -i msg.oga -c copy msg.ogg`) then pass the `.ogg` to this script.
- This utility rejects audio longer than five minutes. For clips just over that
  limit, split with ffmpeg into ≤4.5m chunks and run one pass per chunk (same
  `--language` / `--mode`), then concatenate transcripts in order. Prefer this
  over a Batch STT client unless the user needs diarization or timestamps.
  Example: `ffmpeg -y -i long.m4a -f segment -segment_time 270 -c copy /tmp/chunk_%02d.m4a`
- Audio is uploaded to Sarvam and each pass may be billable. Automatic POST
  retries are disabled so an ambiguous timeout cannot duplicate cost.
- Raw PCM requires an explicit codec and is intentionally outside this simple
  utility's scope.

## Sources

- REST endpoint: https://docs.sarvam.ai/api-reference/speech-to-text/transcribe
- Quickstart: https://docs.sarvam.ai/api/getting-started/quickstart
- API selection: https://docs.sarvam.ai/api/api-guides-tutorials/speech-to-text/which-api-to-use