Instant Voice Cloning API

Use the official sarvamai Python and TypeScript SDKs — the same client shape as Bulbul Text-to-Speech (voice_cloning.convert / convert_stream, plus voice_cloning_streaming for WebSocket). See Libraries & SDKs. Requires sarvamai ≥ 0.1.37 (Python) or ≥ 1.1.12 (TypeScript) for the Instant Voice Cloning surface.

Instant Voice Cloning can follow either path:

1. Saved voice (recommended for reuse): create once with POST /voices/create (or client.voice_cloning.create_voice), then pass voice_id on every generate call.
2. Inline reference clip: send ref_audio (optional ref_text) on each generate call — no saved voice required.

Generate speech with one of:

• POST /voices/clone / voice_cloning.convert — one-shot JSON response with base64 audio
• POST /voices/clone/stream / voice_cloning.convert_stream — binary audio stream as sentences become ready
• GET /voices/clone/ws / voice_cloning_streaming — WebSocket for incremental text and multi-turn sessions

Send exactly one of ref_audio or voice_id on each generate request. Sending both returns 400.

What you get

How it works

Prefer the Python and TypeScript SDKs. Endpoint-level schemas and extra language snippets are on the API Reference.

Quickstart

Install the SDK (pip install "sarvamai>=0.1.37" or npm install sarvamai@1.1.12), then create a voice and synthesize:

import base64
from sarvamai import SarvamAI
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
with open("reference.wav", "rb") as f:
    created = client.voice_cloning.create_voice(
        file=f,
        name="my-voice",
        language="en-IN",
    )
voice_id = created.data.voice_id
response = client.voice_cloning.convert(
    voice_id=voice_id,
    text="नमस्ते, मैं आपकी कैसे मदद कर सकता हूँ?",
)
with open("output.wav", "wb") as out:
    out.write(base64.b64decode(response.audio_b64 or response.audio))

language_code is optional. These examples omit it so the service detects Hindi from the text. Pass language_code when pronunciation has to be exact — see Supported languages.

The one-shot response contains audio / audio_b64 and request_id. See the API Reference for the complete request and response schemas.

Manage saved voices

Voices are shared with Content Studio for the same workspace.

The Starter plan (pay as you go) keeps up to 50 cloned voices across your organization, in Content Studio and the API. Pro and Enterprise plans have higher limits. On any plan, deleting a voice frees a slot. In Content Studio, only the person who created a voice, an organization owner or admin, or a workspace admin can delete it.

Limits and pricing

Generation is billed per character of text. See Pricing.

Explore