POST
/
v1
/
text-to-speech
Text To Speech
curl --request POST \
  --url https://api.typecast.ai/v1/text-to-speech \
  --header 'Content-Type: application/json' \
  --header 'X-API-KEY: <api-key>' \
  --data '{
  "voice_id": "tc_62a8975e695ad26f7fb514d1",
  "text": "Hello. How are you?",
  "model": "ssfm-v21",
  "language": "eng",
  "prompt": {
    "emotion_preset": "normal",
    "emotion_intensity": 1
  },
  "output": {
    "volume": 100,
    "audio_pitch": 0,
    "audio_tempo": 1,
    "audio_format": "wav"
  },
  "seed": 42
}'
This response does not have an example.

Authorizations

​
X-API-KEY
string
header
required

API key for authentication. You can obtain an API key from the Typecast dashboard.

Body

application/json
​
voice_id
string
required

Voice ID in format 'tc_' (Typecast voice) or 'uc_' (User-created voice) followed by a unique identifier (e.g., 'tc_62a8975e695ad26f7fb514d1' for a Typecast voice). See Listing all voices for available voices.

Example:

"tc_62a8975e695ad26f7fb514d1"

​
text
string
required

Text to convert to speech (max 5000 characters, credits consumed based on length, supports multiple languages including English, Korean, Japanese, and Chinese, special characters and punctuation handled automatically)

Example:

"Hello. How are you?"

​
model
enum<string>
required

Voice model to use: ssfm-v21 (Speech Synthesis Foundation Model)

Available options:
ssfm-v21
​
language
string

Language code following ISO 639-3 standard. If not provided, will be auto-detected based on text content.

Supported language codes:

CodeLanguageCodeLanguageCodeLanguage
ENGEnglishJPNJapaneseUKRUkrainian
KORKoreanELLGreekINDIndonesian
SPASpanishTAMTamilDANDanish
DEUGermanTGLTagalogSWESwedish
FRAFrenchFINFinnishMSAMalay
ITAItalianZHOChineseCESCzech
POLPolishSLKSlovakPORPortuguese
NLDDutchARAArabicBULBulgarian
RUSRussianHRVCroatianRONRomanian
Example:

"eng"

​
prompt
object

Emotion and style settings for the generated speech, including emotion type (happy/sad/angry/normal) and intensity (0.0 to 2.0) to control the emotional expression

​
output
object

Audio output settings including volume (0-200), pitch (-12 to +12 semitones), tempo (0.5x to 2.0x), and format (wav/mp3) for controlling the final audio characteristics

​
seed
integer

Random seed for reproducible results (same seed + same parameters = same output, useful for testing, reproducing specific results, and quality control)

Example:

42

Response

Success - Returns audio file

The response is of type file.