Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Sarvam AI / Bulbul

Bulbul v2

Legacy speech synthesis with pitch, pace and loudness controls.

Speech & voice
availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
8 of 19 specification fields collected
Text input limit1,500 characters per REST requestSee specification notes below
Languages11 listedFull language list in specifications
Input billingNot collectedSarvam API
Output billingNot collectedNo inferred price

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
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
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, TeluguSource for Languages (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)

Beta response-audio caching is documented only for v1/v2, not v3/v4 Flash. This is not token-prefix caching.

Maximum prompt characters
1,500 characters per REST requestSource for Maximum prompt characters (opens in a new tab)
Voice controls
Pace 0.3–3; pitch recommended −0.75…0.75; loudness recommended 0.3–3; optional preprocessing.Source for Voice controls (opens in a new tab)
Audio sample rates
8, 16, 22.05 or 24 kHz; default 22.05 kHz.Source for Audio sample rates (opens in a new tab)

The overview loosely says all models accept higher sample rates; the API reference restricts 32/44.1/48 kHz to v3 and v4 Flash.

Access & pricing

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

Sarvam API

Provider source (opens in a new tab)
API model ID
bulbul:v2
Access
Sarvam API subscription key; credit balance and account rate limits apply.
Regions
Model-specific regional routing and contractual data residency require verification.
API endpoint URL
https://api.sarvam.ai/text-to-speechSource for API endpoint URL (opens in a new tab)
Maximum prompt characters
1,500 characters per REST requestSource for Maximum prompt characters (opens in a new tab)
Streaming
Not supportedSource for Streaming (opens in a new tab)

This route returns completed base64 audio; dedicated streaming routes are separate.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Production rights apply to output generated while account credits are consumed, including signup credits, subject to EULA terms. Rights to the underlying model and voices are not transferred.

Read the service policy (opens in a new tab)

Sarvam API

Provider source (opens in a new tab)
API model ID
bulbul:v2
Access
Sarvam API subscription key; credit balance and account rate limits apply.
Regions
Model-specific regional routing and contractual data residency require verification.
API endpoint URL
https://api.sarvam.ai/text-to-speech/streamSource for API endpoint URL (opens in a new tab)
Streaming
SupportedSource for Streaming (opens in a new tab)
Audio sample rates
8, 16, 22.05 or 24 kHz; default 22.05 kHz.Source for Audio sample rates (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Sarvam API

Provider source (opens in a new tab)
API model ID
bulbul:v2
Access
Sarvam API subscription key; credit balance and account rate limits apply.
Regions
Model-specific regional routing and contractual data residency require verification.
API endpoint URL
wss://api.sarvam.ai/text-to-speech/wsSource for API endpoint URL (opens in a new tab)
Streaming
SupportedSource for Streaming (opens in a new tab)
Audio sample rates
8, 16, 22.05 or 24 kHz; default 22.05 kHz.Source for Audio sample rates (opens in a new tab)

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

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

bulbul:v2
Documented

Beta response-audio caching is documented only for v1/v2, not v3/v4 Flash. This is not token-prefix caching.

Support evidence (opens in a new tab)
How it works
Exact-request audio response cacheSource for How it works (opens in a new tab)
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
enable_cached_responses=true; default false.Source for How to enable it (opens in a new tab)
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Only v1/v2; identical requests return cached audio. Cache lifetime and billing discount are not established.Source for Limits & data boundaries (opens in a new tab)

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

Caching reviewed 13 Oct 2026

Sarvam API

bulbul:v2
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

bulbul:v2
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.

Voice choices

7 voices

Choose a voice within Bulbul v2. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
AnushkaanushkaModel-supported languages; no per-voice restriction specifiedNamed preset voice. Speaker IDs are case-sensitive and lowercase.Voice source (opens in a new tab)
ManishamanishaModel-supported languages; no per-voice restriction specifiedNamed preset voice. Speaker IDs are case-sensitive and lowercase.Voice source (opens in a new tab)
VidyavidyaModel-supported languages; no per-voice restriction specifiedNamed preset voice. Speaker IDs are case-sensitive and lowercase.Voice source (opens in a new tab)
AryaaryaModel-supported languages; no per-voice restriction specifiedNamed preset voice. Speaker IDs are case-sensitive and lowercase.Voice source (opens in a new tab)
AbhilashabhilashModel-supported languages; no per-voice restriction specifiedNamed preset voice. Speaker IDs are case-sensitive and lowercase.Voice source (opens in a new tab)
KarunkarunModel-supported languages; no per-voice restriction specifiedNamed preset voice. Speaker IDs are case-sensitive and lowercase.Voice source (opens in a new tab)
HiteshhiteshModel-supported languages; no per-voice restriction specifiedNamed preset voice. Speaker IDs are case-sensitive and lowercase.Voice source (opens in a new tab)

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)

Sources reviewed