Skip to main content
POST
Generate speech from text using ElevenLabs TTS

Body

application/json
caption
string

Caption when sending (used with --send)

execute
boolean

Confirm delivery when --send is used; local generation runs immediately

format
string

Output format: mp3_44100_128 (default), mp3_22050_32, pcm_16000

lang
string

Language code: pt, en, es, etc

model
string

Model: eleven_multilingual_v2, eleven_turbo_v2_5, etc

output
string

Output directory (default: /tmp)

send
boolean

Auto-send generated audio to the current chat

speed
string

Speech speed 0.5-2.0 (default: 1.0)

text
string

Text to convert to speech

textFile
string

Relative .md or .txt file to convert to speech

voice
string

ElevenLabs voice ID

Response

Success — body conforms to the @Returns schema.

audio
object
required
options
object
required
success
boolean
required
sent
object
{key}
any