Blend TTS -> Dual API Test

Flow: Azure TTS (SSML or text) -> one generated clip -> sent to both blend APIs with the same word target.

Target blend word

Voice

Language

TTS speed (prosody rate)

TTS pitch

Pause between sounds (ms)

SSML (optional, used when present) Fallback plain text (used if SSML box is empty)

Scoring audio slow-down (FFmpeg atempo)

Scoring gain (dB)

SuperSpeech slack

No result yet.

No result yet.