Generate ElevenLabs speech with timestamps
Use “Generate ElevenLabs speech with timestamps” in Recued. It runs the ElevenLabs workflow for generating one text-to-speech response as JSON with base64 audio and character alignment timestamps with approval before changes are made.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (10 steps)
normalized_voice_id
trim
Trim whitespace from setting voice id
normalized_text
trim
Trim whitespace from setting text
normalized_model_id
trim
Trim whitespace from setting model id
normalized_reason
trim
Trim whitespace from setting reason
voice
recued-core.elevenlabs.voice.read
Read voice on elevenlabs
default_settings
recued-core.elevenlabs.voice_settings.default.read
Read voice settings default on elevenlabs
create_speech
recued-core.elevenlabs.speech.create
Create speech on elevenlabs
alignment_characters
default
Apply default
alignment_count
count
Count items in alignment characters
card
to_summary
Format results as a summary card
▼
Output
summary
card
json
create_speech.result
json
voice.result
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
text
setting
=
speed
setting
=
1
style
setting
=
0
reason
setting
=
model id
setting
=
eleven_multilingual_v2
voice id
setting
=
stability
setting
=
0.5
output format
setting
=
mp3_44100_128
enable logging
setting
=
true
similarity boost
setting
=
0.75
use speaker boost
setting
=
true
apply text normalization
setting
=
auto
apply language text normalization
setting
=
false
Uses (3 operations)
Pack operation
Read voice on elevenlabs
recued-core.elevenlabs.voice.read
Pack operation
Read voice settings default on elevenlabs
recued-core.elevenlabs.voice_settings.default.read
Pack operation
Create speech on elevenlabs
recued-core.elevenlabs.speech.create
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.