Need to replace ElevenLabs with Edge-TTS

[rajtilakjee]

I have a function that used ElevenLabs API which worked fine. However, it incurred a lot of cost even during prototyping. So I thought it would be best to go for Edge-TTS. I have completed the conversation but now sure if this is a correct implmentation.

Here's the ElevenLabs API code:

from elevenlabs import generate, set_api_key, Voice, VoiceSettings
from pydub import AudioSegment
import io
import os
import hashlib
from utils.os_stuff import get_env_var_or_fail
import logging

set_api_key(get_env_var_or_fail('ELEVEN_LABS_API_KEY'))

HOST_VOICE = Voice(
    voice_id="21m00Tcm4TlvDq8ikWAM",
    name="Rachel",
    category="premade",
    settings=VoiceSettings(stability=0.35, similarity_boost=0.9),
)

ADS_VOICE = Voice(
    voice_id="TxGEqnHWrfWFTfGW9XjX",
    name="Josh",
    category="premade",
    settings=VoiceSettings(stability=0.35, similarity_boost=0.9),
)


def load_audio_bytes(audio_bytes):
    audio_file = io.BytesIO(audio_bytes)
    audio_segment = AudioSegment.from_file(audio_file, format='mp3')
    return audio_segment


def convert_text_to_mp3(text, voice):
    # Generate the cache key by MD5 hashing the text
    cache_key = hashlib.md5(text.encode()).hexdigest()

    # Check if the file already exists in cache
    cache_dir = ".eleven_labs_cache"
    cache_file = os.path.join(cache_dir, f"{cache_key}.mp3")

    if not os.path.exists(cache_dir):
        os.makedirs(cache_dir)

    if os.path.exists(cache_file):
        # If it does exist, load and return as an AudioSegment
        audio_segment = AudioSegment.from_mp3(cache_file)
    else:
        # If it does not exist, call the API, create, save, and return as an AudioSegment
        char_count = len(text)
        logging.info(f'Calling eleven labs for {char_count} chars...')
        section_1_voice_over = load_audio_bytes(generate(
            text=text,
            voice=voice
        ))
        section_1_voice_over.export(cache_file, format='mp3')
        audio_segment = section_1_voice_over

    return audio_segment

And here's the Edge-TTS code:

import asyncio
import edge_tts
from pydub import AudioSegment

VOICE = "en-GB-SoniaNeural"

def convert_text_to_mp3(text):
    loop = asyncio.get_event_loop_policy().get_event_loop()
    try:
        audio_segment = loop.run_until_complete(edge_tts.Communicate(text, VOICE))
    finally:
        loop.close()
        return audio_segment

Can someone please tell me whether it needs any further changes. TIA.

[rajtilakjee]

I am getting an error message:

UnboundLocalError: cannot access local variable 'audio_segment' where it is not associated with a value

[rany2]

Return audio_segment inside the try scope. It will still execute the finally:

import asyncio
import edge_tts
from pydub import AudioSegment

VOICE = "en-GB-SoniaNeural"

def convert_text_to_mp3(text):
    loop = asyncio.get_event_loop_policy().get_event_loop()
    try:
        audio_segment = loop.run_until_complete(edge_tts.Communicate(text, VOICE))
        return audio_segment
    finally:
        loop.close()

[rany2]

To get the mp3, see https://github.com/rany2/edge-tts/blob/master/examples/basic_audio_streaming.py or to just save to a file https://github.com/rany2/edge-tts/blob/master/examples/basic_generation.py

[rajtilakjee]

Thank you so much for the reply. I tried the same but am getting another error. Here's the traceback:

Traceback (most recent call last):
  File "D:\repositories\keepyourmouthshut\app\generate_podcast.py", line 216, in <module>
    main()
  File "D:\repositories\keepyourmouthshut\app\generate_podcast.py", line 212, in main
    gencast(name, desc, topic, advert)
  File "D:\repositories\keepyourmouthshut\app\generate_podcast.py", line 131, in gencast
    edge_tts_stuff.convert_text_to_mp3(text=intro)
  File "D:\repositories\keepyourmouthshut\app\utils\edge_tts_stuff.py", line 10, in convert_text_to_mp3
    audio_segment = loop.run_until_complete(edge_tts.Communicate(text, VOICE))
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Rajtilak\AppData\Local\Programs\Python\Python311\Lib\asyncio\base_events.py", line 632, in run_until_complete
    future = tasks.ensure_future(future, loop=self)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Rajtilak\AppData\Local\Programs\Python\Python311\Lib\asyncio\tasks.py", line 659, in ensure_future
    return _ensure_future(coro_or_future, loop=loop)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Rajtilak\AppData\Local\Programs\Python\Python311\Lib\asyncio\tasks.py", line 674, in _ensure_future
    raise TypeError('An asyncio.Future, a coroutine or an awaitable '
TypeError: An asyncio.Future, a coroutine or an awaitable is required

[rany2]

Have a look at the examples, edge_tts.Communicate() is not a coroutine.

[rajtilakjee]

@rany2 found the solution, its working now! You are great! Thanks so much for this library. Will give you the credits on my README.md. That's the least I can do. Thanks once again.