infery
← All models

ElevenLabs TTS Multilingual v2

elevenlabs-tts-multilingual-v2

Musicby Elevenlabs

Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.

Details

Accepts
text

Pricing

Price
0.013 cr / character

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
textrequiredstringThe text to convert to speech
speednumberSpeech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality.
stylenumberStyle exaggeration (0-1)
voicestringThe voice to use for speech generation
next_text
stabilitynumberVoice stability (0-1)
timestampsbooleanWhether to return timestamps for each word in the generated speech
language_codeLanguage code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model.
previous_text
similarity_boostnumberSimilarity boost (0-1)
apply_text_normalizationstringenum: auto, on, offThis parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped.

Output

FieldTypeDescription
audioThe generated audio file
timestampsTimestamps for each word in the generated speech. Only returned if `timestamps` is set to True in the request.