---
language:
- en
base_model:
- sesame/csm-1b
- senstella/csm-expressiva-1b
- meta-llama/Llama-3.2-1B
- Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct
- fixie-ai/ultravox-v0_5-llama-3_2-1b
pipeline_tag: text-to-speech
---

**The model supports multilingual transcription, but voice output is only in English or English-like languages.**
    
    
Models:   
CSM: [sesame/csm-1b](https://huggingface.co/sesame/csm-1b)     
CSM-EXPRESSIVA(WHISPERING & NO VC): [senstella/csm-expressiva-1b](https://huggingface.co/senstella/csm-expressiva-1b)     
LLAMA: [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B)     
LLAMA-VIKHR: [Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct](https://huggingface.co/Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct)     
LLAMA-ULTRAVOX: [fixie-ai/ultravox-v0_5-llama-3_2-1b](https://huggingface.co/fixie-ai/ultravox-v0_5-llama-3_2-1b)     
   

### CSM:  
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/csm/examples/conversational_a.wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/csm/examples/conversational_b.wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/csm/examples/read_speech_a.wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/csm/examples/read_speech_b.wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/csm/examples/read_speech_c.wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/csm/examples/read_speech_d.wav?download=true" type="audio/mpeg">
</audio>
&nbsp;        

### CSM-EXPRESSIVA(WHISPERING & NO VC):
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/csm-expressiva/examples/demo.wav?download=true" type="audio/mpeg">
</audio>
&nbsp;  

### LLAMA:
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama/real-examples/audio.wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama/real-examples/audio_1(VC).wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama/real-examples/audio_2(VC).wav?download=true" type="audio/mpeg">
</audio>
&nbsp;  

### LLAMA-VIKHR:
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama-vikhr/real-examples/audio.wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama-vikhr/real-examples/audio_1(VC).wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama-vikhr/real-examples/audio_2(VC).wav?download=true" type="audio/mpeg">
</audio>
&nbsp;  

### LLAMA-ULTRAVOX:
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama-ultravox/real-examples/audio.wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama-ultravox/real-examples/audio_1(VC).wav?download=true" type="audio/mpeg">
</audio>
<audio controls>
  <source src="https://huggingface.co/Derur/csm-models/resolve/main/llama-ultravox/real-examples/audio_2(VC).wav?download=true" type="audio/mpeg">
</audio>