curl --request POST \
  --url https://users.rime.ai/v1/rime-tts \
  --header 'Accept: audio/mp3' \
  --header 'Authorization: Bearer <authorization>' \
  --header 'Content-Type: application/json' \
  --data '{
  "speaker": "<string>",
  "text": "<string>",
  "modelId": "arcana",
  "repetition_penalty": 1.5,
  "temperature": 0.5,
  "top_p": 0.5,
  "max_tokens": 1200
}'

​
Fixed Headers

​
Accept
audio/mp3
required

​
Variable Parameters

​
speaker
string
required

Must be one of the flagship Arcana voices listed in our documentation or a string description in the format “gen z woman” or a fictional name like “doe_john”.

​
text
string
required

The text you’d like spoken. Character limit per request is 500 via the API and 1,000 in the dashboard UI.

​
modelId
string

Choose arcana for Rime’s most realistic conversational voices.

​
repetition_penalty
float
default:"1.5"

The repetition penalty. Range is 1 to 2.

​
temperature
float
default:"0.5"

The temperature. Range is 0 to 1.

​
top_p
float
default:"0.5"

The top p. Range is 0 to 1.

​
max_tokens
int
default:"1200"

The max tokens. Range is 200 to 5000.

curl --request POST \
  --url https://users.rime.ai/v1/rime-tts \
  --header 'Accept: audio/mp3' \
  --header 'Authorization: Bearer <authorization>' \
  --header 'Content-Type: application/json' \
  --data '{
  "speaker": "<string>",
  "text": "<string>",
  "modelId": "arcana",
  "repetition_penalty": 1.5,
  "temperature": 0.5,
  "top_p": 0.5,
  "max_tokens": 1200
}'