feat: kokoro tts support (#643)

Co-authored-by: Maciej Majek <[email protected]>

Author: MagdalenaKotynia

docs/setup/vendors.md

@@ -9,12 +9,12 @@ Alternatively vendors can be configured manually in `config.toml` file.
 
 The table summarizes vendor alternative for core AI service and optional RAI modules:
 
-| Module                                          | Open source | Alternative             | Why to consider alternative?                                             | More information                                                                                          |
-| ----------------------------------------------- | ----------- | ----------------------- | ------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------- |
-| [LLM service](#llm-model-configuration-in-rai)  | Ollama      | OpenAI, Bedrock         | Overall performance of the LLM models, supported modalities and features | [LangChain models](https://docs.langchain4j.dev/integrations/language-models/)                            |
-| **Optional:** [Tracing tool](./tracing.md)      | Langfuse    | LangSmith               | Better integration with LangChain                                        | [Comparison](https://langfuse.com/faq/all/langsmith-alternative)                                          |
-| **Optional:** [Text to speech](#text-to-speech) | OpenTTS     | ElevenLabs              | Arguably, significantly better voice synthesis                           | <li> [OpenTTS GitHub](https://github.com/synesthesiam/opentts) </li><li> [RAI voice interface][s2s] </li> |
-| **Optional:** [Speech to text](#speech-to-text) | Whisper     | OpenAI Whisper (hosted) | When suitable local GPU is not an option                                 | <li> [Whisper GitHub](https://github.com/openai/whisper) </li><li> [RAI voice interface][s2s] </li>       |
+| Module                                          | Open source        | Alternative             | Why to consider alternative?                                             | More information                                                                                                                                                                 |
+| ----------------------------------------------- | ------------------ | ----------------------- | ------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [LLM service](#llm-model-configuration-in-rai)  | Ollama             | OpenAI, Bedrock         | Overall performance of the LLM models, supported modalities and features | [LangChain models](https://docs.langchain4j.dev/integrations/language-models/)                                                                                                   |
+| **Optional:** [Tracing tool](./tracing.md)      | Langfuse           | LangSmith               | Better integration with LangChain                                        | [Comparison](https://langfuse.com/faq/all/langsmith-alternative)                                                                                                                 |
+| **Optional:** [Text to speech](#text-to-speech) | KokoroTTS, OpenTTS | ElevenLabs              | Arguably, significantly better voice synthesis                           | <li> [KokoroTTS](https://huggingface.co/hexgrad/Kokoro-82M#usage) </li><li> [OpenTTS GitHub](https://github.com/synesthesiam/opentts) </li><li> [RAI voice interface][s2s] </li> |
+| **Optional:** [Speech to text](#speech-to-text) | Whisper            | OpenAI Whisper (hosted) | When suitable local GPU is not an option                                 | <li> [Whisper GitHub](https://github.com/openai/whisper) </li><li> [RAI voice interface][s2s] </li>                                                                              |
 
 > [!TIP] Best-performing AI models
 >

docs/speech_to_speech/sounddevice.md

@@ -31,6 +31,9 @@ connector = SoundDeviceConnector(
 )
 ```
 
+> [!TIP]
+> If you're experiencing audio issues and device_name is set to 'default', try specifying the exact device name instead, as this often resolves the problem.
+
 ## Message Type: `SoundDeviceMessage`
 
 ```python

examples/s2s/tts.py

@@ -18,7 +18,7 @@
 
 import rclpy
 
-from rai_s2s import OpenTTS, TextToSpeechAgent
+from rai_s2s import KokoroTTS, OpenTTS, TextToSpeechAgent
 from rai_s2s.sound_device import SoundDeviceConfig
 
 
@@ -35,6 +35,14 @@ def parse_arguments():
         help="Speaker device name (default: 'default')",
     )
 
+    parser.add_argument(
+        "--tts-model",
+        type=str,
+        choices=["opentts", "kokoro"],
+        default="kokoro",
+        help="TTS model to use: 'opentts' or 'kokoro' (default: 'kokoro')",
+    )
+
     # Use parse_known_args to ignore unknown arguments
     args, unknown = parser.parse_known_args()
 
@@ -55,7 +63,12 @@ def parse_arguments():
         # device_name="Jabra Speak2 40 MS: USB Audio (hw:2,0)",
         device_name=args.device_name,
     )
-    tts = OpenTTS()
+
+    tts = KokoroTTS()
+    print("Using KokoroTTS model")
+    if args.tts_model == "opentts":
+        tts = OpenTTS()
+        print("Using OpenTTS model")
 
     agent = TextToSpeechAgent(config, "text_to_speech", tts)
     agent.run()