Eleven Labs module not running

[TBsheets805]

I have generated voiceover scripts from Claude and put into Airtable. I would like to take each of the 5 scripts from Airtable and create audio with Eleven Labs but I keep getting the following Runtime Error

[400] {“detail”:{“status”:“model_can_not_do_text_to_speech”,“message”:“The selected model can not be used for text to speech”}}

I’m somewhat new to Make, can someone let me know what I’m doing wrong and how to fix?

[Anshul_Soni]

Hey @TBsheets805 , you can use HTTPS request module instead of elevenlabs for converting text to speech, and refer this docs for API - Text To Speech - ElevenLabs

[TBsheets805]

@Anshul_Soni Ok thank you. In the HTTPS module, where do I put the Data and Response info?

data = {
  "text": "Born and raised in the charming south, 
  I can add a touch of sweet southern hospitality 
  to your audiobooks and podcasts",
  "model_id": "eleven_monolingual_v1",
  "voice_settings": {
    "stability": 0.5,
    "similarity_boost": 0.5
  }
}

response = requests.post(url, json=data, headers=headers)
with open('output.mp3', 'wb') as f:
    for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
        if chunk:
            f.write(chunk)

[Anshul_Soni]

@TBsheets805 you need to also add the header, with specific authorization

[TBsheets805]

@Anshul_Soni this is the output I’m getting…

[jjjw]

Having the same error. It appears the “eleven_english_sts_v2” voice model does not work – and in fact many do not work, only the ones with ‘turbo’ seem to work.

I think the deeper issue is actually that certain voices only work with certain models. So try picking a different voice!

[Ivan_perez]

Hi, jjjw is right. I had same issue [400] {“detail”:{“status”:… and it got resolved simply by changing to model Eleven Turbo v2.5. I assume this model model might consume more of your ElevenLab’s Credit quota but you can try out and compare. BR

[jjjw]

I actually think ‘turbo’ is less money

Glad to hear it helped.