elevenlabssynthesizer
Text to Speech filter, using ElevenLabs
Hierarchy
GObject ╰──GInitiallyUnowned ╰──GstObject ╰──GstElement ╰──elevenlabssynthesizer
Factory details
Authors: – Mathieu Duponchelle
Classification: – Audio/Text/Filter
Rank – none
Plugin – elevenlabs
Package – gst-plugin-elevenlabs
Pad Templates
src
audio/x-raw:
rate: { (int)22050, (int)48000, (int)44100, (int)24000, (int)16000, (int)8000 }
channels: 1
layout: interleaved
format: S16LE
Properties
language-code
“language-code” gchararray
An optional language code (ISO 639-1), useful with certain models
Flags : Read / Write
Default value : NULL
latency
“latency” guint
Amount of milliseconds to allow ElevenLabs
Flags : Read / Write
Default value : 2000
model-id
“model-id” gchararray
ElevenLabs Model ID, see https://help.elevenlabs.io/hc/en-us/articles/21811236079505-How-do-I-find-the-model-ID
Flags : Read / Write
Default value : eleven_flash_v2_5
overflow
“overflow” GstElevenLabsOverflow *
Defines how output audio with a longer duration than input text should be handled
Flags : Read / Write
Default value : clip (0)
retry-with-speed
“retry-with-speed” gboolean
When synthesis results in larger duration, retry with higher speed
Flags : Read / Write
Default value : true
voice-id
“voice-id” gchararray
ElevenLabs Voice ID, see https://elevenlabs.io/app/voice-library
Flags : Read / Write
Default value : 9BWtsMINqrJLrRacOk9x
Named constants
GstElevenLabsOverflow
Members
clip
(0) – Clip
overlap
(1) – Overlap
shift
(2) – Shift
The results of the search are