From d255e954d6aaa885bed86330e74c3653e451c24e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleix=20Conchillo=20Flaqu=C3=A9?= <aleix@daily.co>
Date: Thu, 8 Aug 2024 22:29:40 -0700
Subject: [PATCH] services(elevenlabs): allow specifying output_format

---
 CHANGELOG.md                       |  3 +++
 src/pipecat/services/elevenlabs.py | 11 ++++++++---
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b9d727a9b..63dbda5bd 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- `ElevenLabsTTSService` can now specify ElevenLabs input parameters such as
+  `output_format`.
+
 - `TwilioFrameSerializer` can now specify Twilio's and Pipecat's desired sample
   rates to use.
 
diff --git a/src/pipecat/services/elevenlabs.py b/src/pipecat/services/elevenlabs.py
index cc63d189a..0de629034 100644
--- a/src/pipecat/services/elevenlabs.py
+++ b/src/pipecat/services/elevenlabs.py
@@ -6,7 +6,8 @@
 
 import aiohttp
 
-from typing import AsyncGenerator
+from typing import AsyncGenerator, Literal
+from pydantic import BaseModel
 
 from pipecat.frames.frames import AudioRawFrame, ErrorFrame, Frame, MetricsFrame
 from pipecat.services.ai_services import TTSService
@@ -15,6 +16,8 @@ from loguru import logger
 
 
 class ElevenLabsTTSService(TTSService):
+    class InputParams(BaseModel):
+        output_format: Literal["pcm_16000", "pcm_22050", "pcm_24000", "pcm_44100"] = "pcm_16000"
 
     def __init__(
             self,
@@ -23,12 +26,14 @@ class ElevenLabsTTSService(TTSService):
             voice_id: str,
             aiohttp_session: aiohttp.ClientSession,
             model: str = "eleven_turbo_v2_5",
+            params: InputParams = InputParams(),
             **kwargs):
         super().__init__(**kwargs)
 
         self._api_key = api_key
         self._voice_id = voice_id
         self._model = model
+        self._params = params
         self._aiohttp_session = aiohttp_session
 
     def can_generate_metrics(self) -> bool:
@@ -46,8 +51,8 @@ class ElevenLabsTTSService(TTSService):
         payload = {"text": text, "model_id": self._model}
 
         querystring = {
-            "output_format": "pcm_16000",
-            "optimize_streaming_latency": 2}
+            "output_format": self._params.output_format
+        }
 
         headers = {
             "xi-api-key": self._api_key,