From 656cbc35e1233681224d1d05dadb5ae8574a0e61 Mon Sep 17 00:00:00 2001
From: Mark Backman <mark@daily.co>
Date: Thu, 19 Dec 2024 12:11:07 -0500
Subject: [PATCH] Make auto_mode an input parametere for ElevenLabsTTSService;
 add changelog entry

---
 CHANGELOG.md                       | 10 +++++++++-
 src/pipecat/services/elevenlabs.py |  4 +++-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 526775b16..5bdd1cd67 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -12,12 +12,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added `DailyTransport.send_dtmf()` to send dial-out DTMF tones.
 
 - Added `DailyTransport.sip_call_transfer()` to forward SIP and PSTN calls to
-  another address or number.  For example, transfer a SIP call to a different
+  another address or number. For example, transfer a SIP call to a different
   SIP address or transfer a PSTN phone number to a different PSTN phone number.
 
 - Added `DailyTransport.sip_refer()` to transfer incoming SIP/PSTN calls from
   outside Daily to another SIP/PSTN address.
 
+- Added an `auto_mode` input parameter to `ElevenLabsTTSService`. `auto_mode`
+  is set to `True` by default. Enabling this setting disables the chunk
+  schedule and all buffers, which reduces latency.
+
 - Added `KoalaFilter` which implement on device noise reduction using Koala
   Noise Suppression.
   (see https://picovoice.ai/platform/koala/)
@@ -51,6 +55,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 
+- `auto_mode: True` for the `ElevenLabsTTSService`. This change
+  significantly reduces the latency by disabling the chunk schedule and all
+  buffers.
+
 - `OpenAIRealtimeBetaLLMService` now takes a `model` parameter in the
   constructor.
 
diff --git a/src/pipecat/services/elevenlabs.py b/src/pipecat/services/elevenlabs.py
index e5310003b..cffa90025 100644
--- a/src/pipecat/services/elevenlabs.py
+++ b/src/pipecat/services/elevenlabs.py
@@ -135,6 +135,7 @@ class ElevenLabsTTSService(WordTTSService):
         similarity_boost: Optional[float] = None
         style: Optional[float] = None
         use_speaker_boost: Optional[bool] = None
+        auto_mode: Optional[bool] = True
 
         @model_validator(mode="after")
         def validate_voice_settings(self):
@@ -193,6 +194,7 @@ class ElevenLabsTTSService(WordTTSService):
             "similarity_boost": params.similarity_boost,
             "style": params.style,
             "use_speaker_boost": params.use_speaker_boost,
+            "auto_mode": str(params.auto_mode).lower(),
         }
         self.set_model_name(model)
         self.set_voice(voice_id)
@@ -312,7 +314,7 @@ class ElevenLabsTTSService(WordTTSService):
             voice_id = self._voice_id
             model = self.model_name
             output_format = self._settings["output_format"]
-            url = f"{self._url}/v1/text-to-speech/{voice_id}/stream-input?model_id={model}&output_format={output_format}&auto_mode=true"
+            url = f"{self._url}/v1/text-to-speech/{voice_id}/stream-input?model_id={model}&output_format={output_format}&auto_mode={self._settings['auto_mode']}"
 
             if self._settings["optimize_streaming_latency"]:
                 url += f"&optimize_streaming_latency={self._settings['optimize_streaming_latency']}"