Composed engine
The sarvam voice engine
Indian languages end to end. Sarvam Saaras v3 transcribes, the Sarvam-105B model reasons, and Bulbul v3 speaks, so Hindi, Tamil, Telugu and the other Indian languages Sarvam supports are handled by models built for them rather than by an English pipeline with a language flag.
Last updated
$0.0623per connected minute, including the $0.012 orchestration fee
What sarvam runs, and what each part costs
A composed engine is three stages, each billed in its own unit. The per-minute column is what that unit adds up to at typical speech rates. The pipeline label is Sarvam, Indian languages end to end.
| Stage | Model | Unit price | Per minute |
|---|---|---|---|
| Speech-to-text | sarvam/saaras-v3-realtime | $0.0001 per second | $0.0076 |
| Language model | sarvam/sarvam-105b | $0.0000 per token in | $0.0011 |
| Language model | sarvam/sarvam-105b | $0.0000 per token out | $0.0005 |
| Text-to-speech | sarvam/bulbul-v3 | $0.0000 per character | $0.0411 |
| Orchestration | wixzel/orchestration | $0.0120 per minute | $0.0120 |
Rounded up, never down. Where two models are listed for one stage the engine picks by language; the engine price above assumes the dearer path. All prices on the model price list.
Frequently asked questions
- What is the sarvam voice engine?
- sarvam is a composed voice engine on Wixzel Phone. Indian languages end to end. Sarvam Saaras v3 transcribes, the Sarvam-105B model reasons, and Bulbul v3 speaks, so Hindi, Tamil, Telugu and the other Indian languages Sarvam supports are handled by models built for them rather than by an English pipeline with a language flag.
- How much does the sarvam engine cost per minute?
- $0.0623 per connected minute at typical speech rates, including the flat $0.012 per minute orchestration fee. The figure is generated from the price book the meter bills against and is rounded up, never down. Telephony runs over your own SIP trunk and is not included or marked up.
- Which models does the sarvam engine use?
- sarvam runs
sarvam/saaras-v3-realtime,sarvam/sarvam-105b,sarvam/bulbul-v3. Each stage is billed in its own unit: seconds of speech recognised, tokens in and out of the model, and characters synthesised. - Do I need my own sarvam account to use sarvam?
- No. The provider accounts belong to Wixzel Phone. One
wv_live_…API key and a prepaid balance cover the sarvam engine and every other engine; there are no provider keys to bring. - How do I use the sarvam engine in a call?
- Name the three stages in the agent's voice when you create it with
POST /v1/agents, for example the stt, llm and tts refs listed above, then place a call withPOST /v1/calls.GET /v1/engineslists what is available right now; an engine whose provider is degraded disappears from that list before calls start failing. - Is the sarvam price per minute a flat rate?
- No. $0.0623 is what a typical minute adds up to. The meter charges per second of speech, per token and per character for the models that actually ran, plus the flat orchestration fee, and every micro-dollar is itemised in
GET /v1/usage/events. A quieter or shorter turn costs less; a long monologue costs more.