ComfyUI Node
TS Silero TTS
Silero TTS v5_3_ru with ComfyUI AUDIO output.
TS Silero TTS
- audio
◄text►
◄input_formattext►
◄speakerxenia►
◄run_devicegpu►
◄enable_chunkingtrue►
◄max_chunk_chars900►
◄chunk_pause_ms120►
◄put_accenttrue►
◄put_yotrue►
◄put_stress_homotrue►
◄put_yo_homotrue►
CategoryTS/Audio
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | Text or SSML content for speech synthesis. | |
| input_format | COMBO | text | Input mode: plain text or SSML. |
| speaker | COMBO | xenia | Silero speaker voice. |
| run_device | COMBO | gpu | Execution device for Silero model. |
| enable_chunking | BOOLEAN | true | Automatically split long text into chunks to avoid Silero length limits. |
| max_chunk_chars | INT | 900200–4000 | Approximate maximum characters per chunk. |
| chunk_pause_ms | INT | 1200–3000 | Silence between generated chunks in milliseconds. |
| put_accent | BOOLEAN | true | Add stress marks to common words where user did not provide them. |
| put_yo | BOOLEAN | true | Replace e with yo where needed. |
| put_stress_homo | BOOLEAN | true | Add stress marks for homographs without yo. |
| put_yo_homo | BOOLEAN | true | Add stress marks for homographs with yo. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | Synthesized speech audio. |