ComfyUI Node
Seed Speech 2.0 · Text to Speech
41 voices with tone set in plain language 10.8 credits ($0.108) per 1k characters. Model: bytedance/seed-speech-2.0/text-to-speech Fields, prices and examples: https://popnow.ai/docs/models/seed-speech-2-0
Seed Speech 2.0 · Text to Speech
- audio
- task id
◄text►
◄voice_idstokie_en►
◄instructions►
◄speed1.00►
◄pitch0►
◄volume1.00►
◄languagemodel default►
◄output_formatmp3►
◄sample_ratemodel default►
CategoryPopNow/Audio/ByteDance
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | The words to be spoken, exactly as written. Billed per 1,000 characters. | |
| voice_id | COMBO | stokie_en | Preset voice. The suffix shows the languages it is built for. |
| instructions | STRING | How to read the text: tone, emotion, pace or volume. Not spoken and not billed. | |
| speed | FLOAT | 1.000.5–2 | Speaking rate; 1 is the voice's normal pace. |
| pitch | INT | 0-12–12 | Pitch shift in semitones; 0 keeps the voice's own pitch. |
| volume | FLOAT | 1.000.5–2 | Loudness multiplier; 1 is the normal level. |
| language | COMBO | model default | Forces the reading language. Leave empty to detect it from the text. |
| output_format | COMBO | mp3 | File format of the result; opus is an Ogg Opus file. |
| sample_rate | COMBO | model default | Sample rate in Hz. The model uses 24000 when omitted. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | Several results come back as a batch; Save Audio writes one file each. |
| task id | STRING | The PopNow task id, for the API console logs or support. |