ComfyUI Node
IndexTTS2 Script Dubbing (SRT)
A ComfyUI node in audio/IndexTTS2 with 24 inputs and 1 output.
IndexTTS2 Script Dubbing (SRT)
- model
- emo_audio_prompt
- voice_1
- voice_2
- voice_3
- voice_4
- voice_5
- voice_6
- voice_7
- audio
◄script_srt1
00:00:01,000 --> 00:00:03,000
唐僧：悟空，你又调皮了。
2
00:00:04,000 --> 00:00:06,000
孙悟空：师父，俺老孙冤枉啊！
►
◄emo_alpha1.0►
◄temperature1.0►
◄top_k0►
◄top_p1.00►
◄use_randomfalse►
◄save_segmentsfalse►
◄segments_prefixdubbing►
◄voice_1_name►
◄voice_2_name►
◄voice_3_name►
◄voice_4_name►
◄voice_5_name►
◄voice_6_name►
◄voice_7_name►
Categoryaudio/IndexTTS2
Inputs (24)
| Name | Type | Default | Description |
|---|---|---|---|
| model | INDEXTTS2_MODEL | — | |
| script_srt | STRING | 1 00:00:01,000 --> 00:00:03,000 唐僧：悟空，你又调皮了。 2 00:00:04,000 --> 00:00:06,000 孙悟空：师父，俺老孙冤枉啊！ | — |
| emo_alpha | FLOAT | 1.00–2 | — |
| temperature | FLOAT | 1.00.1–2 | — |
| top_k | INT | 00–100 | — |
| top_p | FLOAT | 1.000–1 | — |
| use_random | BOOLEAN | false | — |
| save_segments | BOOLEAN | false | — |
| segments_prefix | STRING | dubbing | — |
| emo_audio_promptopt | AUDIO | — | |
| voice_1opt | AUDIO | — | |
| voice_1_nameopt | STRING | — | |
| voice_2opt | AUDIO | — | |
| voice_2_nameopt | STRING | — | |
| voice_3opt | AUDIO | — | |
| voice_3_nameopt | STRING | — | |
| voice_4opt | AUDIO | — | |
| voice_4_nameopt | STRING | — | |
| voice_5opt | AUDIO | — | |
| voice_5_nameopt | STRING | — | |
| voice_6opt | AUDIO | — | |
| voice_6_nameopt | STRING | — | |
| voice_7opt | AUDIO | — | |
| voice_7_nameopt | STRING | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |