feat: add deepgram tts extension with voice-assistant integration

ai_agents/agents/examples/voice-assistant/tenapp/manifest.json

@@ -152,6 +152,9 @@
     },
     {
       "path": "../../../ten_packages/extension/oracle_tts_python"
+    },
+    {
+      "path": "../../../ten_packages/extension/deepgram_tts"
     }
   ],
   "scripts": {

ai_agents/agents/examples/voice-assistant/tenapp/property.json

@@ -185,6 +185,190 @@
           ]
         }
       },
+      {
+        "name": "voice_assistant_deepgram_tts",
+        "auto_start": false,
+        "graph": {
+          "nodes": [
+            {
+              "type": "extension",
+              "name": "agora_rtc",
+              "addon": "agora_rtc",
+              "extension_group": "default",
+              "property": {
+                "app_id": "${env:AGORA_APP_ID}",
+                "app_certificate": "${env:AGORA_APP_CERTIFICATE|}",
+                "channel": "ten_agent_test",
+                "stream_id": 1234,
+                "remote_stream_id": 123,
+                "subscribe_audio": true,
+                "publish_audio": true,
+                "publish_data": true,
+                "enable_agora_asr": false
+              }
+            },
+            {
+              "type": "extension",
+              "name": "stt",
+              "addon": "deepgram_asr_python",
+              "extension_group": "stt",
+              "property": {
+                "params": {
+                  "api_key": "${env:DEEPGRAM_API_KEY}",
+                  "language": "en-US",
+                  "model": "nova-3"
+                }
+              }
+            },
+            {
+              "type": "extension",
+              "name": "llm",
+              "addon": "openai_llm2_python",
+              "extension_group": "chatgpt",
+              "property": {
+                "base_url": "https://api.openai.com/v1",
+                "api_key": "${env:OPENAI_API_KEY}",
+                "frequency_penalty": 0.9,
+                "model": "${env:OPENAI_MODEL}",
+                "max_tokens": 512,
+                "prompt": "",
+                "proxy_url": "${env:OPENAI_PROXY_URL|}",
+                "greeting": "TEN Agent connected. How can I help you today?",
+                "max_memory_length": 10
+              }
+            },
+            {
+              "type": "extension",
+              "name": "tts",
+              "addon": "deepgram_tts",
+              "extension_group": "tts",
+              "property": {
+                "dump": false,
+                "dump_path": "/tmp",
+                "params": {
+                  "api_key": "${env:DEEPGRAM_API_KEY}",
+                  "model": "aura-2-thalia-en",
+                  "encoding": "linear16",
+                  "sample_rate": 24000
+                }
+              }
+            },
+            {
+              "type": "extension",
+              "name": "main_control",
+              "addon": "main_python",
+              "extension_group": "control",
+              "property": {
+                "greeting": "TEN Agent connected. How can I help you today?"
+              }
+            },
+            {
+              "type": "extension",
+              "name": "message_collector",
+              "addon": "message_collector2",
+              "extension_group": "transcriber",
+              "property": {}
+            },
+            {
+              "type": "extension",
+              "name": "weatherapi_tool_python",
+              "addon": "weatherapi_tool_python",
+              "extension_group": "default",
+              "property": {
+                "api_key": "${env:WEATHERAPI_API_KEY|}"
+              }
+            },
+            {
+              "type": "extension",
+              "name": "streamid_adapter",
+              "addon": "streamid_adapter",
+              "property": {}
+            }
+          ],
+          "connections": [
+            {
+              "extension": "main_control",
+              "cmd": [
+                {
+                  "names": [
+                    "on_user_joined",
+                    "on_user_left"
+                  ],
+                  "source": [
+                    {
+                      "extension": "agora_rtc"
+                    }
+                  ]
+                },
+                {
+                  "names": [
+                    "tool_register"
+                  ],
+                  "source": [
+                    {
+                      "extension": "weatherapi_tool_python"
+                    }
+                  ]
+                }
+              ],
+              "data": [
+                {
+                  "name": "asr_result",
+                  "source": [
+                    {
+                      "extension": "stt"
+                    }
+                  ]
+                }
+              ]
+            },
+            {
+              "extension": "agora_rtc",
+              "audio_frame": [
+                {
+                  "name": "pcm_frame",
+                  "dest": [
+                    {
+                      "extension": "streamid_adapter"
+                    }
+                  ]
+                },
+                {
+                  "name": "pcm_frame",
+                  "source": [
+                    {
+                      "extension": "tts"
+                    }
+                  ]
+                }
+              ],
+              "data": [
+                {
+                  "name": "data",
+                  "source": [
+                    {
+                      "extension": "message_collector"
+                    }
+                  ]
+                }
+              ]
+            },
+            {
+              "extension": "streamid_adapter",
+              "audio_frame": [
+                {
+                  "name": "pcm_frame",
+                  "dest": [
+                    {
+                      "extension": "stt"
+                    }
+                  ]
+                }
+              ]
+            }
+          ]
+        }
+      },
       {
         "name": "voice_assistant_oracle",
         "auto_start": false,

ai_agents/agents/ten_packages/extension/deepgram_tts/README.md

@@ -0,0 +1,103 @@
+# Deepgram TTS Extension
+
+A TEN Framework extension that provides Text-to-Speech (TTS) capabilities using Deepgram's Aura streaming API.
+
+## Features
+
+- Real-time streaming TTS via WebSocket
+- Multiple voice models (Aura-2 series)
+- Configurable sample rates (8000, 16000, 24000, 48000 Hz)
+- Linear16 PCM audio output
+- TTFB (Time to First Byte) metrics reporting
+- Audio dump capability for debugging
+
+## Configuration
+
+### Properties
+
+| Property | Type | Default | Description |
+|----------|------|---------|-------------|
+| `params.api_key` | string | Required | Deepgram API key |
+| `params.model` | string | `aura-2-thalia-en` | Voice model to use |
+| `params.encoding` | string | `linear16` | Audio encoding format |
+| `params.sample_rate` | int | `24000` | Output sample rate in Hz |
+| `params.base_url` | string | `wss://api.deepgram.com/v1/speak` | WebSocket endpoint |
+| `params.<deepgram_query_param>` | scalar | Optional | Additional Deepgram websocket query parameters passed through to the vendor |
+| `dump` | bool | `false` | Enable audio dumping |
+| `dump_path` | string | `/tmp` | Path for audio dump files |
+
+### Example Configuration
+
+```json
+{
+  "params": {
+    "api_key": "${env:DEEPGRAM_API_KEY}",
+    "model": "aura-2-thalia-en",
+    "encoding": "linear16",
+    "sample_rate": 24000,
+    "container": "none"
+  },
+  "dump": false,
+  "dump_path": "/tmp"
+}
+```
+
+Known extension-owned keys such as `api_key`, `base_url`, `model`, `encoding`,
+and `sample_rate` are normalized onto the config object. Any remaining scalar
+keys under `params` are appended to the Deepgram websocket query string.
+
+## Available Voice Models
+
+Deepgram Aura-2 voices:
+- `aura-2-thalia-en` - Female, English (default)
+- `aura-2-luna-en` - Female, English
+- `aura-2-stella-en` - Female, English
+- `aura-2-athena-en` - Female, English
+- `aura-2-hera-en` - Female, English
+- `aura-2-orion-en` - Male, English
+- `aura-2-arcas-en` - Male, English
+- `aura-2-perseus-en` - Male, English
+- `aura-2-angus-en` - Male, English
+- `aura-2-orpheus-en` - Male, English
+- `aura-2-helios-en` - Male, English
+- `aura-2-zeus-en` - Male, English
+
+## Supported Sample Rates
+
+- 8000 Hz
+- 16000 Hz
+- 24000 Hz (recommended)
+- 48000 Hz
+
+## API Interface
+
+This extension implements the standard TEN TTS interface:
+
+### Input Data
+- `tts_text_input` - Text to synthesize
+- `tts_flush` - Flush pending audio
+
+### Output Data
+- `tts_audio_start` - Audio generation started
+- `tts_audio_end` - Audio generation completed
+- `metrics` - Performance metrics (TTFB, duration)
+- `error` - Error information
+
+### Output Audio
+- `pcm_frame` - PCM audio data (16-bit, mono)
+
+## Running Tests
+
+```bash
+cd deepgram_tts
+tman -y install --standalone
+./tests/bin/start
+```
+
+## Environment Variables
+
+- `DEEPGRAM_API_KEY` - Your Deepgram API key
+
+## License
+
+Apache License, Version 2.0

ai_agents/agents/ten_packages/extension/deepgram_tts/__init__.py

@@ -0,0 +1,6 @@
+#
+# This file is part of TEN Framework, an open source project.
+# Licensed under the Apache License, Version 2.0.
+# See the LICENSE file for more information.
+#
+from . import addon

ai_agents/agents/ten_packages/extension/deepgram_tts/addon.py

@@ -0,0 +1,20 @@
+#
+# This file is part of TEN Framework, an open source project.
+# Licensed under the Apache License, Version 2.0.
+# See the LICENSE file for more information.
+#
+from ten_runtime import (
+    Addon,
+    register_addon_as_extension,
+    TenEnv,
+)
+
+
+@register_addon_as_extension("deepgram_tts")
+class DeepgramTTSExtensionAddon(Addon):
+
+    def on_create_instance(self, ten_env: TenEnv, name: str, context) -> None:
+        from .extension import DeepgramTTSExtension
+
+        ten_env.log_info("DeepgramTTSExtensionAddon on_create_instance")
+        ten_env.on_create_instance_done(DeepgramTTSExtension(name), context)