Skip to main content
POST
https://api.unify.ai
/
v0
/
assistant
/
voice
/
generate
curl --request POST \
  --url 'https://api.unify.ai/v0/assistant/voice/generate' \
  --header "Authorization: Bearer $UNIFY_KEY" \
  --header 'Content-Type: application/json' \
  --data '{}'

{}
Generates audio from text using the specified provider and voice.

​
Authorizations

​
Authorization
string
required
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

​
Body

​
text
string
required
Text to synthesize.
​
provider
string
required
TTS provider.
​
voice_id
string
required
Provider-specific voice ID for the speech.
​
model_id
string | null
Provider-specific model ID (e.g., ‘sonic-2’ for Cartesia, ‘eleven_multilingual_v2’ for ElevenLabs, ‘gpt-4o-mini-tts’ for OpenAI).
​
output_format
string
default:"mp3"
Desired audio output format. This will determine the Content-Type of the response.
​
cartesia_language
string | null
default:"en"
Language code for Cartesia TTS (e.g., ‘en’). If None, Cartesia attempts auto-detection.
​
cartesia_sample_rate
integer | null
Optional sample rate for Cartesia (e.g., 24000, 44100). Provider defaults used if None.
​
cartesia_bit_rate
integer | null
Optional bit rate for Cartesia lossy formats like MP3 (e.g., 128000). Provider defaults used if None. Not for PCM.
​
elevenlabs_optimize_streaming_latency
integer | null
0-4. Optimize for streaming latency for ElevenLabs.
​
elevenlabs_voice_settings_stability
number | null
Stability for ElevenLabs voice settings.
​
elevenlabs_voice_settings_similarity_boost
number | null
Similarity boost for ElevenLabs voice settings.
curl --request POST \
  --url 'https://api.unify.ai/v0/assistant/voice/generate' \
  --header "Authorization: Bearer $UNIFY_KEY" \
  --header 'Content-Type: application/json' \
  --data '{}'

{}