[Feature] Edge Text to speech #34

README.md

@@ -121,7 +121,8 @@ cd SillyTavern-extras
 | `summarize` | Text summarization                | ✔️ Yes    |
 | `classify`  | Text sentiment classification     | ✔️ Yes      |
 | `sd`        | Stable Diffusion image generation | :x: No (✔️ remote)      |
-| `tts`       | [Silero TTS server](https://github.com/ouoertheo/silero-api-server) | :x: No |
+| `silero-tts`       | [Silero TTS server](https://github.com/ouoertheo/silero-api-server) | :x: No |
+| `edge-tts` | [Microsoft Edge TTS client](https://github.com/rany2/edge-tts) | ✔️ Yes |
 | `chromadb`  | Infinity context server           | :x: No |
 
 
@@ -308,7 +309,7 @@ None
 { "previous_model": "name of the previous model", "current_model": "name of the newly loaded model" }
 ```
 
-### Generate TTS voice
+### Generate Silero TTS voice
 `POST /api/tts/generate`
 #### **Input**
 ```
@@ -317,7 +318,7 @@ None
 #### **Output**
 WAV audio file.
 
-### Get TTS voices
+### Get Silero TTS voices
 `GET /api/tts/speakers`
 #### **Output**
 ```
@@ -330,7 +331,7 @@ WAV audio file.
 ]
 ```
 
-### Get TTS voice sample
+### Get Silero TTS voice sample
 `GET /api/tts/sample/<voice_id>`
 #### **Output**
 WAV audio file.
@@ -400,3 +401,19 @@ WAV audio file.
 ```
 { "chat_id": "chat1 - 2023-04-12" }
 ```
+
+### Get a list of Edge TTS voices
+`GET /api/edge-tts/list`
+#### **Output**
+```
+[{'Name': 'Microsoft Server Speech Text to Speech Voice (af-ZA, AdriNeural)', 'ShortName': 'af-ZA-AdriNeural', 'Gender': 'Female', 'Locale': 'af-ZA', 'SuggestedCodec': 'audio-24khz-48kbitrate-mono-mp3', 'FriendlyName': 'Microsoft Adri Online (Natural) - Afrikaans (South Africa)', 'Status': 'GA', 'VoiceTag': {'ContentCategories': ['General'], 'VoicePersonalities': ['Friendly', 'Positive']}}]
+```
+
+### Generate Edge TTS voice
+`POST /api/edge-tts/generate`
+#### **Input**
+```
+{ "text": "Text to narrate", "voice": "af-ZA-AdriNeural" }
+```
+#### **Output**
+MP3 audio file.

requirements-complete.txt

@@ -14,4 +14,5 @@ transformers==4.28.1
 diffusers==0.16.1
 silero-api-server
 chromadb
-sentence_transformers
+sentence_transformers
+edge-tts

requirements.txt

@@ -7,4 +7,5 @@ colorama
 --extra-index-url https://download.pytorch.org/whl/cu117
 torch==2.0.0+cu117
 transformers==4.28.1
-webuiapi
+webuiapi
+edge-tts

server.py

@@ -3,6 +3,7 @@ from flask import (
     Flask,
     jsonify,
     request,
+    Response,
     render_template_string,
     abort,
     send_from_directory,
@@ -207,6 +208,12 @@ elif "sd" in modules and sd_use_remote:
         modules.remove("sd")
 
 if "tts" in modules:
+    print("tts module is deprecated. Please use silero-tts instead.")
+    modules.remove("tts")
+    modules.append("silero-tts")
+
+
+if "silero-tts" in modules:
     if not os.path.exists(SILERO_SAMPLES_PATH):
         os.makedirs(SILERO_SAMPLES_PATH)
     print("Initializing Silero TTS server")
@@ -218,6 +225,12 @@ if "tts" in modules:
         tts_service.update_sample_text(SILERO_SAMPLE_TEXT)
         tts_service.generate_samples()
 
+
+if "edge-tts" in modules:
+    print("Initializing Edge TTS client")
+    import tts_edge as edge
+
+
 if "chromadb" in modules:
     print("Initializing ChromaDB")
     import chromadb
@@ -609,6 +622,7 @@ def get_modules():
 
 
 @app.route("/api/tts/speakers", methods=["GET"])
+@require_module("silero-tts")
 def tts_speakers():
     voices = [
         {
@@ -622,6 +636,7 @@ def tts_speakers():
 
 
 @app.route("/api/tts/generate", methods=["POST"])
+@require_module("silero-tts")
 def tts_generate():
     voice = request.get_json()
     if "text" not in voice or not isinstance(voice["text"], str):
@@ -639,10 +654,36 @@ def tts_generate():
 
 
 @app.route("/api/tts/sample/<speaker>", methods=["GET"])
+@require_module("silero-tts")
 def tts_play_sample(speaker: str):
     return send_from_directory(SILERO_SAMPLES_PATH, f"{speaker}.wav")
 
 
+@app.route("/api/edge-tts/list", methods=["GET"])
+@require_module("edge-tts")
+def edge_tts_list():
+    voices = edge.get_voices()
+    return jsonify(voices)
+
+
+@app.route("/api/edge-tts/generate", methods=["POST"])
+@require_module("edge-tts")
+def edge_tts_generate():
+    data = request.get_json()
+    if "text" not in data or not isinstance(data["text"], str):
+        abort(400, '"text" is required')
+    if "voice" not in data or not isinstance(data["voice"], str):
+        abort(400, '"voice" is required')
+    # Remove asterisks
+    data["text"] = data["text"].replace("*", "")
+    try:
+        audio = edge.generate_audio(text=data["text"], voice=data["voice"])
+        return Response(audio, mimetype="audio/mpeg")
+    except Exception as e:
+        print(e)
+        abort(500, data["voice"])
+
+
 @app.route("/api/chromadb", methods=["POST"])
 @require_module("chromadb")
 def chromadb_add_messages():

tts_edge.py

@@ -0,0 +1,32 @@
+import io
+import edge_tts
+import asyncio
+
+
+def get_voices():
+    voices = asyncio.run(edge_tts.list_voices())
+    return voices
+
+
+async def _iterate_chunks(audio):
+    async for chunk in audio.stream():
+        if chunk["type"] == "audio":
+            yield chunk["data"]
+
+
+async def _async_generator_to_list(async_gen):
+    result = []
+    async for item in async_gen:
+        result.append(item)
+    return result
+
+
+def generate_audio(text: str, voice: str) -> bytes:
+    audio = edge_tts.Communicate(text, voice)
+    chunks = asyncio.run(_async_generator_to_list(_iterate_chunks(audio)))
+    buffer = io.BytesIO()
+
+    for chunk in chunks:
+        buffer.write(chunk)
+    
+    return buffer.getvalue()