Skip to main content
POST
/
v1
/
tts
/
slng
/
rime
/
arcana:de
Arcana v2 (German)
curl --request POST \
  --url https://api.slng.ai/v1/tts/slng/rime/arcana:de \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "Hallo von Rime Arcana Deutsch. Test der Sprachsynthese.",
  "speaker": "lorelei"
}
'
"<string>"

Authorizations

​
Authorization
string
header
required

API key issued by SLNG. Pass as Authorization: Bearer <token>.

Headers

​
X-Region-Override
enum<string>

Target region override. Auto-selected if not provided.

Available options:
eu-north-1

Body

application/json

Rime Arcana TTS request for German.

​
speaker
enum<string>
default:sigurd
required

Voice speaker ID (German voices).

Available options:
bergmann_katharina,
lorelei,
rosenfeld_steffi,
runa,
sigurd
​
text
string
required

Text to synthesize.

Minimum string length: 1
​
modelId
enum<string>
default:arcana

Model: arcana (most realistic, ~150ms), mistv2 (speed & control, ~70ms).

Available options:
arcana,
arcana-3,
mistv2,
mist
​
repetition_penalty
number<float>
default:1.5

The repetition penalty. We do not recommend changing this from the default value. Typical range is 1 to 2. Float that penalizes new tokens based on whether they appear in the prompt and the generated text so far. Values > 1 encourage the model to use new tokens, while values < 1 encourage the model to repeat tokens.

​
temperature
number<float>
default:0.5

The temperature. We do not recommend changing this from the default value. Typical range is 0 to 1. Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling.

​
top_p
number<float>
default:1

The top p. We do not recommend changing this from the default value. Typical range is 0 to 1. Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens.

​
audioFormat
enum<string>
default:mp3

Output audio format.

Available options:
mp3,
wav,
pcm,
s16le,
mulaw,
ulaw
​
sampleRate
enum<integer>
default:22050

Output sample rate in Hz.

Available options:
8000,
16000,
22050,
44100,
48000
​
speed
number
default:1

Speech rate multiplier (0.25 = half speed, 2.0 = double speed).

Required range: 0.25 <= x <= 2
​
sample_rate
enum<integer>
default:22050

Alias for provider-specific sample rate param.

Available options:
8000,
16000,
22050,
44100,
48000
​
language
enum<string>
default:en

Alias for provider-specific language param.

Available options:
en,
es,
fr,
de,
ar,
he,
hi,
ja,
pt
​
encoding
enum<string>
default:mp3

Alias for provider-specific encoding param.

Available options:
mp3,
wav,
pcm,
linear16,
ulaw
​
segment
enum<string>
default:bySentence

Controls text segmentation for synthesis. 'immediate' synthesizes without waiting, 'never' waits for explicit flush/EOS, 'bySentence' waits for complete sentences.

Available options:
immediate,
never,
bySentence

Response

Synthesis successful.

Binary audio data.