resemble-ai/chatterbox-pro 🔢❓📝 → 🖼️

⭐ Official ▶️ 13.1K runs 📅 Jun 2025 ⚙️ Cog 0.15.5
expressive-tts text-to-speech watermarked-audio

About

Generate expressive, natural speech with Resemble AI's Chatterbox.

Example Output

Prompt:

"Poppin' bottles in the ice, like a blizzard.
When we drink, we do it right, gettin' slizzered
Sippin' sizzurp in my ride (in my ride) like Three 6.
Now I'm feelin' so fly like a G 6"

Output

Example output

Performance Metrics

4.71s Prediction Time
4.72s Total Time
All Input Parameters
{
  "pitch": "medium",
  "voice": "William (Whispering)",
  "prompt": "Poppin' bottles in the ice, like a blizzard.\nWhen we drink, we do it right, gettin' slizzered\nSippin' sizzurp in my ride (in my ride) like Three 6.\nNow I'm feelin' so fly like a G 6",
  "temperature": 0.8,
  "exaggeration": 0.5
}
Input Parameters
seed Type: integer
Random seed. Set for reproducible generation
pitch Default: medium
Pitch
voice Default: Luna
Choose a predefined voice
prompt (required) Type: string
Text to synthesize
temperature Type: numberDefault: 0.8Range: 0.1 - 5
Temperature
custom_voice Type: string
The uuid of the voice to use (this overrides the voice selection)
exaggeration Type: numberDefault: 0.5Range: 0.1 - 1
Exaggeration (Neutral = 0.5, extreme values can be unstable)
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Using seed: 717931943
Warning: Moderation check failed
Synthesizing speech with voice e2180df0...
Version Details
Version ID
301e12652e84fbba1524e5f2758a9a92c6bd205792304f53c057b7f9ab091342
Version Created
June 18, 2025
Run on Replicate →