Adds a TTS Benchmark Suite

[cezarc1]

Adds a TTS benchmark suite for 11labs, cartesia and playht.

Uses raw websocket for 11labs, cartesia. For playht using the provided python sdk w/ GRPC as I could not figure out what the grpc address was.

Each service was configured to be as fast as possible, however each service's api's are unique so I might have missed something.

TTFU - I came up with this on my own. There is TTFB but I thought this was more specific? ¯_(ツ)_/¯.

Also updates the Readme, accordingly.

Example output:

poetry run python tts_benchmark_suite.py "It's simple: Overspecialize, and you breed in weakness. It's slow death."
17:45:03 - INFO - Benchmarking Eleven Labs - websocket...
17:45:06 - INFO - Eleven Labs - websocket: (TTFU) time to first utterance: 312.93ms
17:45:06 - INFO - Eleven Labs - websocket: Average chunk latency: 230.71ms
17:45:06 - INFO - Eleven Labs - websocket: Total chunks received: 12
17:45:06 - INFO - Eleven Labs - websocket: Total processing time: 2768.55ms
17:45:06 - INFO - ----------------------------------------
17:45:06 - INFO - Benchmarking Cartesia - websocket...
17:45:09 - INFO - Cartesia - websocket: (TTFU) time to first utterance: 187.41ms
17:45:09 - INFO - Cartesia - websocket: Average chunk latency: 58.56ms
17:45:09 - INFO - Cartesia - websocket: Total chunks received: 47
17:45:09 - INFO - Cartesia - websocket: Total processing time: 2752.38ms
17:45:09 - INFO - ----------------------------------------
17:45:09 - INFO - Benchmarking PlayHT - GRPC Python SDK...
17:45:11 - INFO - PlayHT - GRPC Python SDK: (TTFU) time to first utterance: 201.89ms
17:45:11 - INFO - PlayHT - GRPC Python SDK: Average chunk latency: 16.33ms
17:45:11 - INFO - PlayHT - GRPC Python SDK: Total chunks received: 122
17:45:11 - INFO - PlayHT - GRPC Python SDK: Total processing time: 1991.93ms
17:45:11 - INFO - ----------------------------------------