I have this simple sentence:
"Once upon a time in the quiet village of Elmdale, lived a 7-year-old."
And to get each word timestamped I create this SSML:
<speak> <mark name="1 Once"/>Once <mark name="2 upon"/>upon <mark name="3 a"/>a <mark name="4 time"/>time <mark name="5 in"/>in <mark name="6 the"/>the <mark name="7 quiet"/>quiet <mark name="8 village"/>village <mark name="9 of"/>of <mark name="10 Elmdale,"/>Elmdale, <mark name="11 lived"/>lived <mark name="12 a"/>a <mark name="13 7-year-old."/>7-year-old. </speak>
The results I keep getting back are:
[
{ timeSeconds: 0, markName: '13 7-year-old.' },
{ timeSeconds: 0.039887867867946625, markName: '1 Once' },
{ timeSeconds: 0.3389071524143219, markName: '2 upon' },
{ timeSeconds: 0.6277555823326111, markName: '3 a' },
{ timeSeconds: 0.7206619381904602, markName: '4 time' },
{ timeSeconds: 1.0438523292541504, markName: '5 in' },
{ timeSeconds: 1.1475272178649902, markName: '6 the' },
{ timeSeconds: 1.220619559288025, markName: '7 quiet' },
{ timeSeconds: 1.6282528638839722, markName: '8 village' },
{ timeSeconds: 1.9669618606567383, markName: '9 of' },
{ timeSeconds: 2.0707359313964844, markName: '10 Elmdale,' },
{ timeSeconds: 2.9641265869140625, markName: '11 lived' },
{ timeSeconds: 3.2229373455047607, markName: '12 a' }
]
Any suggestions?
LinkedIn
Twitter
