Merge pull request #1423 from pipecat-ai/aleix/elevenlabs-pcm-8000

ElevenLabs: add support for a sample rate of 8000

CHANGELOG.md

@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+
+- ElevenLabs TTS services now support a sample rate of 8000.
+
 ### Fixed
 
 - Fixed an issue in `UltravoxSTTService` that caused improper audio processing

dev-requirements.txt

@@ -3,10 +3,10 @@ coverage~=7.6.12
 grpcio-tools~=1.67.1
 pip-tools~=7.4.1
 pre-commit~=4.0.1
-pyright~=1.1.394
+pyright~=1.1.397
 pytest~=8.3.4
 pytest-asyncio~=0.25.3
-ruff~=0.9.7
+ruff~=0.11.1
 setuptools~=70.0.0
 setuptools_scm~=8.1.0
 python-dotenv~=1.0.1

src/pipecat/services/elevenlabs.py

@@ -102,6 +102,8 @@ def language_to_elevenlabs_language(language: Language) -> Optional[str]:
 
 def output_format_from_sample_rate(sample_rate: int) -> str:
     match sample_rate:
+        case 8000:
+            return "pcm_8000"
         case 16000:
             return "pcm_16000"
         case 22050:
@@ -113,7 +115,7 @@ def output_format_from_sample_rate(sample_rate: int) -> str:
     logger.warning(
         f"ElevenLabsTTSService: No output format available for {sample_rate} sample rate"
     )
-    return "pcm_16000"
+    return "pcm_24000"
 
 
 def build_elevenlabs_voice_settings(

src/pipecat/services/ultravox.py

@@ -17,25 +17,19 @@ from loguru import logger
 
 from pipecat.frames.frames import (
     AudioRawFrame,
-    LLMFullResponseEndFrame,
-    LLMFullResponseStartFrame,
-    LLMTextFrame,
-    TranscriptionFrame,
-    TextFrame,
-    StartFrame,
-    EndFrame,
     CancelFrame,
     EndFrame,
     ErrorFrame,
     Frame,
+    LLMFullResponseEndFrame,
+    LLMFullResponseStartFrame,
+    LLMTextFrame,
     StartFrame,
-    TranscriptionFrame,
     UserStartedSpeakingFrame,
     UserStoppedSpeakingFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.ai_services import AIService
-from pipecat.utils.time import time_now_iso8601
 
 try:
     from transformers import AutoTokenizer