English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Zero-shot text-to-speech aims at synthesizing voices with unseen speechprompts. Previous large-scale multispeaker TTS models have successfullyachieved this goal with an enrolled recording within 10 seconds. However, mostof them are designed to utilize only short speech prompts. The limitedinformation in short speech prompts significantly hinders the performance offine-grained identity imitation. In this paper, we introduce Mega-TTS 2, ageneric zero-shot multispeaker TTS model that is capable of synthesizing speechfor unseen speakers with arbitrary-length prompts. Specifically, we 1) design amulti-reference timbre encoder to extract timbre information from multiplereference speeches; 2) and train a prosody language model with arbitrary-lengthspeech prompts; With these designs, our model is suitable for prompts ofdifferent lengths, which extends the upper bound of speech quality forzero-shot text-to-speech. Besides arbitrary-length prompts, we introducearbitrary-source prompts, which leverages the probabilities derived frommultiple P-LLM outputs to produce expressive and controlled prosody.Furthermore, we propose a phoneme-level auto-regressive duration model tointroduce in-context learning capabilities to duration modeling. Experimentsdemonstrate that our method could not only synthesize identity-preservingspeech with a short prompt of an unseen speaker but also achieve improvedperformance with longer speech prompts. Audio samples can be found inhttps://mega-tts.github.io/mega2_demo/.

Mega-TTS 2: Zero-Shot Text-to-Speech with Arbitrary Length Speech Prompts