Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Sarvam AI / Voice Cloning

Instant Voice Cloning

Speech synthesis from a saved voice or reference recording, with cross-language output and optional quality checks.

previewClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
10 of 21 specification fields collected
Text input limit1,000 REST/HTTP stream; 2,500 per WebSocket text messageSee specification notes below
Languages12 listedFull language list in specifications
Input billingSee ratesSarvam API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Bengali, English, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu, AssameseSource for Languages (opens in a new tab)

12 explicitly accepted language codes. Marketing mentions of 13 are not substituted for the API enum.

Context caching
Not supportedSource for Context caching (opens in a new tab)

enable_cached_responses is accepted but currently ignored; marked coming soon.

Maximum prompt characters
1,000 REST/HTTP stream; 2,500 per WebSocket text messageSource for Maximum prompt characters (opens in a new tab)
Reference audio
Inline clip: one speaker, at most 15 seconds / 10 MB. Voice creation upload limit: 50 MB; 10–15 seconds recommended.Source for Reference audio (opens in a new tab)
Output formats
WAV, MP3, FLAC, Opus, AAC, Linear16, μ-law, A-lawSource for Output formats (opens in a new tab)
Audio sample rates
8, 16, 22.05, 24, 32, 44.1 or 48 kHz; default 24 kHz. Explicit Opus rates restricted to 8/16/24/48 kHz.Source for Audio sample rates (opens in a new tab)
Voice controls
Pace 0.5–2; mutually exclusive with maximum duration. Optional QC for short one-shot generations; off by default and adds latency.Source for Voice controls (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

API model ID
Not collected

A route or service is documented, but a stable version-specific checkpoint selector has not been established.

Access
Sarvam API subscription key; credit balance and account rate limits apply. Beta voice-cloning capability must be enabled.
Regions
Model-specific regional routing and contractual data residency require verification.
API endpoint URL
https://api.sarvam.ai/voices/cloneSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
speechCloned speech synthesis1₹30.0010K characters

Rate conditions

  1. Instant Voice Cloning; input text characters, rounded to nearest character. No inferred cache savings.
Pricing source (opens in a new tab)

Data & enterprise terms

Voice cloning requires authorization to use the reference voice. Credit-consuming output has production rights subject to EULA terms.

Read the service policy (opens in a new tab)
API model ID
Not collected

A route or service is documented, but a stable version-specific checkpoint selector has not been established.

Access
Sarvam API subscription key; credit balance and account rate limits apply. Beta voice-cloning capability must be enabled.
Regions
Model-specific regional routing and contractual data residency require verification.
API endpoint URL
https://api.sarvam.ai/voices/clone/streamSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
speechCloned speech synthesis1₹30.0010K characters

Rate conditions

  1. Instant Voice Cloning; input text characters, rounded to nearest character. No inferred cache savings.
Pricing source (opens in a new tab)

Data & enterprise terms

Voice cloning requires authorization to use the reference voice. Credit-consuming output has production rights subject to EULA terms.

Read the service policy (opens in a new tab)
API model ID
Not collected

A route or service is documented, but a stable version-specific checkpoint selector has not been established.

Access
Sarvam API subscription key; credit balance and account rate limits apply. Beta voice-cloning capability must be enabled.
Regions
Model-specific regional routing and contractual data residency require verification.
API endpoint URL
wss://api.sarvam.ai/voices/clone/wsSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
speechCloned speech synthesis1₹30.0010K characters

Rate conditions

  1. Instant Voice Cloning; input text characters, rounded to nearest character. No inferred cache savings.
Pricing source (opens in a new tab)

Data & enterprise terms

Voice cloning requires authorization to use the reference voice. Credit-consuming output has production rights subject to EULA terms.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Sarvam API

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Sarvam API

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred for this exact native API release/service from provider documentation and review of Sarvam’s public weight inventory. No weights for this identity were identified. Public Sarvam language/translation weights and hosted third-party weights are excluded. A named service or version does not establish an independently disclosed checkpoint.

Classification evidence (opens in a new tab)

Lifecycle dates

Voice cloning API announced26 Sept 2026Source (opens in a new tab)
Streaming added1 Oct 2026Source (opens in a new tab)

Sources reviewed