← All models
Generate expressive, natural speech with Resemble AI's Chatterbox. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.
Details
- Accepts
- text + audio
Pricing
- Price
- 2.5 cr / minute
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| cfg | number | Classifier-free guidance scale (CFG) controls the conditioning factor. Range typically 0.2 to 1.0. For expressive or dramatic speech, try lower cfg values (e.g. ~0.3) and increase exaggeration to around 0.7 or higher. If the reference speaker has a fast speaking style, lowering cfg to around 0.3 can… |
| seed | integer | Useful to control the reproducibility of the generated audio. Assuming all other properties didn't change, a fixed seed should always generate the exact same audio file. Set to 0 for random seed. |
| text | string | Text to synthesize into speech. |
| voice | stringenum: Aurora, Blade, Britney, Carl, Cliff, Richard… | The voice to use for the TTS request. If neither voice nor audio are provided, a random voice will be used. |
| audio_url | string | URL to the audio sample to use as a voice prompt for zero-shot TTS voice cloning. Providing a audio sample will override the voice setting. If neither voice nor audio_url are provided, a random voice will be used. |
| temperature | number | Controls the randomness of generation. Range typically 0.05 to 5. |
| exaggeration | number | Controls emotion exaggeration. Range typically 0.25 to 2.0. |
| high_quality_audio | boolean | If True, the generated audio will be upscaled to 48kHz. The generation of the audio will take longer, but the quality will be higher. If False, the generated audio will be 24kHz. |
| target_voice | stringenum: Aurora, Blade, Britney, Carl, Cliff, Richard… | The voice to use for the speech-to-speech request. If neither target_voice nor target_voice_audio_url are provided, a random target voice will be used. |
| source_audio_url | string | URL to the source audio file to be voice-converted. |
| target_voice_audio_url | string | URL to the audio file which represents the voice of the output audio. If provided, this will override the target_voice setting. If neither target_voice nor target_voice_audio_url are provided, the default target voice will be used. |
Output
| Field | Type | Description |
|---|---|---|
| audio | — | The generated audio file. |