Bytes and SSE stream audio from a complete transcript; WebSocket supports incremental text and audio. Retired snapshots are retained for historical reference.
Professional Voice Clone explicitly fine-tunes these supported snapshots. Requires Startup or higher and at least 30 minutes of single-speaker audio. Training can take up to three hours.
generation_config is supported on Sonic 3 and newer. PVC voices learn pacing and volume from their training data, so runtime speed and volume have no effect on PVC output.
Family alias follows the stable offering; the dated selector pins a snapshot.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 12 Oct 2026
Category
Usage
Rate
Unit
Subscription credit overage
Scale overage1
$38.00
1M credits
Subscription credit overage
Startup overage2
$45.00
1M credits
Subscription credit overage
Pro overage3
$65.00
1M credits
Rate conditions
Scale subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Startup subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Pro subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Enterprise customers may opt into ZDR for TTS/STT inference content; operational metadata is retained. Voice cloning and fine-tuning are excluded. General terms permit model improvement/training unless separately agreed or an opt-out is processed.
Family alias follows the stable offering; the dated selector pins a snapshot.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 12 Oct 2026
Category
Usage
Rate
Unit
Subscription credit overage
Scale overage1
$38.00
1M credits
Subscription credit overage
Startup overage2
$45.00
1M credits
Subscription credit overage
Pro overage3
$65.00
1M credits
Rate conditions
Scale subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Startup subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Pro subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Enterprise customers may opt into ZDR for TTS/STT inference content; operational metadata is retained. Voice cloning and fine-tuning are excluded. General terms permit model improvement/training unless separately agreed or an opt-out is processed.
Family alias follows the stable offering; the dated selector pins a snapshot.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 12 Oct 2026
Category
Usage
Rate
Unit
Subscription credit overage
Scale overage1
$38.00
1M credits
Subscription credit overage
Startup overage2
$45.00
1M credits
Subscription credit overage
Pro overage3
$65.00
1M credits
Rate conditions
Scale subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Startup subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Pro subscription required. Charged only beyond included credits with overages enabled; monthly subscription fees are additional. These are credit prices, not per-million-token or per-million-character rates. Convert using this endpoint's documented credit meter.
Enterprise customers may opt into ZDR for TTS/STT inference content; operational metadata is retained. Voice cloning and fine-tuning are excluded. General terms permit model improvement/training unless separately agreed or an opt-out is processed.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 12 Oct 2026
Voice choices
5 voices
Choose a voice within Cartesia Sonic 3.6 (2026-08-27). These are API voice identifiers, not additional model releases. Source links document each voice.
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
Service terms prohibit downloading or distributing the hosted models and reserve provider model rights. These Sonic/Ink service variants are not in the reviewed official public-weight inventory. Classification is specific to the served variant: public Rene, Llamba, Mamba and H-Net weights are excluded; Ink Whisper is a provider-specific derivative, not a reclassification of baseline Whisper.
