Cartesia

Cartesia’s tuning is passed in synthesizer.options. Which fields take effect depends on the model family, because Cartesia moved these controls between API versions.

1 {
2   "verb": "say",
3   "text": "Thanks for calling, how can I help you today?",
4   "synthesizer": {
5     "vendor": "cartesia",
6     "language": "en",
7     "voice": "a0e99841-438c-4a64-b679-ae501e7d6091",
8     "options": {
9       "speed": -0.3,
10       "emotion": "positivity:high"
11     }
12   }
13 }

Options

speed

number

Speaking rate. Defaults to 0.0. Negative values are slower, positive faster.

emotion

string

An emotion tag in name:level form — for example positivity:high. Supported names are anger, positivity, surprise, sadness and curiosity; levels are lowest, low, high and highest (not every combination is offered for every emotion).

volume

number

Output volume. Applies to the sonic-3 family only.

max_buffer_delay_ms

number

How long Cartesia may buffer incoming text before synthesising, in milliseconds. Raising it can improve prosody across token boundaries at the cost of latency. Not exposed in the portal — set it on the verb.

Model family differences

speed, emotion and volume are sent differently depending on the model, and a control sent to the wrong family is ignored:

sonic-3 and later — sent as generation_config. All three of speed, emotion and volume apply.
sonic-2 — sent as experimental voice controls. Only speed and emotion apply; volume has no effect.

If a speed or emotion setting appears to do nothing, check which model the credential is using before assuming the value is wrong.

Streaming

Cartesia supports TTS streaming, including a native cancel for barge-in and word-level timestamps for alignment.