ElevenLabsTTS
ElevenLabs text-to-speech (TTS) provider.Constructor
ElevenLabs API key. Falls back to the
ELEVENLABS_API_KEY environment variable when omitted.Voice ID to synthesize with. Default
'21m00Tcm4TlvDq8ikWAM'.ElevenLabs model ID. Default
'eleven_turbo_v2'.
Other common values include 'eleven_multilingual_v2' and 'eleven_flash_v2'.Output audio sample rate in Hz. Default
24000.Voice consistency vs. expressiveness. Range 0-1. Default
0.5.How closely the output matches the original voice. Range 0-1. Default
0.75.Style exaggeration. Range 0-1. Default
0.0.Boosts similarity to the original speaker. Default
true.Text normalization mode (e.g. expanding numbers and abbreviations).
Typical values:
'auto', 'on', 'off'. Default null (provider default).Request per-word timestamps alongside the audio. Default
false.Speaking rate multiplier. Default
null (provider default).Language code hint for synthesis (e.g.
'en'). Default null (auto).Whether to parse SSML markup in the input text. Default
null (provider default).Stream audio as it is generated rather than waiting for the full result. Default
true.Native ElevenLabs voice settings object. Used to populate voice parameters
(
stability, similarityBoost, style, useSpeakerBoost) only where the
corresponding top-level option was left at its default. Default null.close
closeEmitter
emit
getRuntimeConfig
interrupt
listenerCount
off
on
once
onFirstAudioByte
removeAllListeners
synthesize
text on the active session.
ElevenLabsTTSModel
Supported ElevenLabs TTS model names.ElevenLabsVoiceSettings
ElevenLabs voice settings, mirroring ElevenLabs’ nativevoice_settings shape.
Provided as an alternative to the top-level ElevenLabsTTSOptions fields
(stability, similarityBoost, style, useSpeakerBoost). A value here is
only applied when the corresponding top-level option is left at its default.
Fields
Voice consistency vs. expressiveness. Range 0-1. Lower is more varied/expressive.
How closely the output matches the original voice. Range 0-1.
Style exaggeration. Range 0-1. Higher amplifies the speaker’s style.
Boosts similarity to the original speaker.