Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -1,20 +1,20 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
emoji: 🦀
|
4 |
colorFrom: yellow
|
5 |
colorTo: purple
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 5.
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: apache-2.0
|
11 |
-
short_description: Text-to-speech using Gradio, FastAPI, and
|
12 |
tags:
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
---
|
19 |
|
20 |
# Voice Chat Assistant
|
@@ -24,7 +24,7 @@ A conversational voice assistant powered by AI that responds to your spoken quer
|
|
24 |
|
25 |
- Speech Recognition: Uses OpenAI's Whisper model to accurately transcribe your voice
|
26 |
- Natural Language Understanding: Leverages Cohere's LLM API for intelligent responses
|
27 |
-
- Text-to-Speech: Generates natural speech using
|
28 |
- Reply on Pause: Automatically responds when you finish speaking
|
29 |
- Conversation History: Maintains context throughout your dialogue
|
30 |
|
@@ -34,7 +34,7 @@ Speak into your microphone and the assistant will respond with voice!
|
|
34 |
## How It Works
|
35 |
- Your voice is transcribed to text using Whisper
|
36 |
- The text is processed by Cohere's LLM to generate a response
|
37 |
-
- The response is converted to speech using
|
38 |
- The conversation continues with full context retention
|
39 |
|
40 |
## Technical Details
|
|
|
1 |
---
|
2 |
+
title: Command_RTC
|
3 |
emoji: 🦀
|
4 |
colorFrom: yellow
|
5 |
colorTo: purple
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 5.32.1
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: apache-2.0
|
11 |
+
short_description: Text-to-speech using Gradio, FastAPI, and Chatterbox TTS
|
12 |
tags:
|
13 |
+
- chatterbox-tts
|
14 |
+
- text-to-speech
|
15 |
+
- voice-cloning
|
16 |
+
- gradio
|
17 |
+
- fastapi
|
18 |
---
|
19 |
|
20 |
# Voice Chat Assistant
|
|
|
24 |
|
25 |
- Speech Recognition: Uses OpenAI's Whisper model to accurately transcribe your voice
|
26 |
- Natural Language Understanding: Leverages Cohere's LLM API for intelligent responses
|
27 |
+
- Text-to-Speech: Generates natural speech using Chatterbox-TTS
|
28 |
- Reply on Pause: Automatically responds when you finish speaking
|
29 |
- Conversation History: Maintains context throughout your dialogue
|
30 |
|
|
|
34 |
## How It Works
|
35 |
- Your voice is transcribed to text using Whisper
|
36 |
- The text is processed by Cohere's LLM to generate a response
|
37 |
+
- The response is converted to speech using Chatterbox-TTS
|
38 |
- The conversation continues with full context retention
|
39 |
|
40 |
## Technical Details
|