Migrating Speech-to-Text from ElevenLabs to Sarvam

This guide covers migrating ElevenLabs speech-to-text (transcription) API calls to Sarvam. If you’re building a full voice agent rather than transcribing audio directly, start from the LiveKit or Pipecat voice agent build guides instead: they aren’t a 1:1 API swap and aren’t covered here.

Quick start

Base URL and auth header change the same way for every ElevenLabs migration, so they’re folded in here rather than in a separate page:

With that, replace the synchronous transcription call:

1
from elevenlabs import ElevenLabs
2
3
client = ElevenLabs(api_key="YOUR_ELEVENLABS_API_KEY")
4
5
with open("audio.mp3", "rb") as f:
6
    transcription = client.speech_to_text.convert(
7
        file=f,
8
        model_id="scribe_v2",
9
        language_code="eng",
10
        tag_audio_events=True,
11
    )
12
13
print(transcription.text)

The rest of this page covers the full endpoint and parameter mapping, diarization via the Batch API, streaming, and common mistakes.

Endpoint map

Parameter concept map

Diarization and long-form audio

ElevenLabs’ /v1/speech-to-text has no separate mode for this; Sarvam’s Batch API handles both:

1
from elevenlabs import ElevenLabs
2
3
client = ElevenLabs(api_key="YOUR_ELEVENLABS_API_KEY")
4
5
transcription = client.speech_to_text.convert(
6
    file=open("meeting.mp3", "rb"),
7
    model_id="scribe_v2",
8
    diarize=True,
9
    num_speakers=3,
10
    webhook=True,
11
)

See the Batch API guide for webhook setup and its Speaker Diarization section for the current per-job speaker limit.

Streaming

What’s different by design

• One current model, not a version matrix. ElevenLabs’ scribe_v1, scribe_v2, and scribe_v2_realtime become a single saaras:v3, used the same way across REST, Batch, and Streaming.
• Direct file upload, no third-party fetch. Sarvam transcribes the file you send it. Download the source once (from a URL, cloud storage, or elsewhere) and upload it directly, so every request starts from the same predictable input.
• Diarization and long-form audio share one workflow. The Batch API handles speaker diarization, files up to 2 hours, and multiple files per job in a single job-based flow, using the same with_diarization/num_speakers parameters whether the request is a short call or a large batch.
• A consistent response shape. Whether diarization is on or off, Sarvam always returns the same transcript (plus diarized_transcript when enabled), rather than switching structure based on a multichannel or output-style flag.
• Indian language depth is Sarvam’s specific strength. Saaras v3 covers 22 Indian languages, including Assamese, Konkani, Kashmiri, Sindhi, Sanskrit, Santali, Manipuri, Bodo, Maithili, and Dogri, with dedicated verbatim, translit, and codemix output modes for code-mixed speech like Hinglish.

Full example

A small wrapper function, before and after, showing the complete set of changes together:

1
from elevenlabs import ElevenLabs
2
3
client = ElevenLabs(api_key="YOUR_ELEVENLABS_API_KEY")
4
5
def transcribe(path: str) -> str:
6
    with open(path, "rb") as f:
7
        transcription = client.speech_to_text.convert(
8
            file=f,
9
            model_id="scribe_v2",
10
            language_code="eng",
11
            tag_audio_events=True,
12
        )
13
    return transcription.text

Common mistakes

See also

• Migration overview: base URL, auth, and SDK client changes
• Which Speech-to-Text API to Use
• Batch API
• Streaming API
• Speaker Diarization
• Errors & Troubleshooting