TTS

POST https://aihubmix.com/v1/audio/speech

Authorization: Bearer $AIHUBMIX_API_KEY
Content-Type: application/json

curl https://aihubmix.com/v1/audio/speech \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tts-1",
    "input": "The quick brown fox jumped over the lazy dog.",
    "voice": "alloy"
  }' \
  --output speech.mp3

curl https://aihubmix.com/v1/audio/speech \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-preview-tts",
    "input": "Say cheerfully: Have a wonderful day!",
    "voice": "Kore",
    "response_format": "wav"
  }' \
  --output speech.wav

curl https://aihubmix.com/v1/audio/speech \
  -H "Authorization: Bearer $AIHUBMIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-preview-tts",
    "input": "TTS the following conversation between Joe and Jane:\nJoe: How'\''s it going today Jane?\nJane: Not too bad, how about you?",
    "voice": "Kore",
    "response_format": "wav",
    "instructions": "Joe should sound firm and professional, Jane should sound upbeat and friendly"
  }' \
  --output conversation.wav

from openai import OpenAI

client = OpenAI(
    api_key="your-aihubmix-api-key",
    base_url="https://aihubmix.com/v1"
)

response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="The quick brown fox jumped over the lazy dog."
)

response.stream_to_file("speech.mp3")

from openai import OpenAI

client = OpenAI(
    api_key="your-aihubmix-api-key",
    base_url="https://aihubmix.com/v1"
)

# Single Speaker
response = client.audio.speech.create(
    model="gemini-2.5-flash-preview-tts",
    voice="Kore",
    input="Say cheerfully: Have a wonderful day!",
    extra_body={
        "response_format": "wav"
    }
)

response.stream_to_file("speech.wav")

# Multi-Speaker Dialogue
conversation_response = client.audio.speech.create(
    model="gemini-2.5-flash-preview-tts",
    voice="Kore",
    input="""TTS the following conversation between Joe and Jane:
    Joe: How's it going today Jane?
    Jane: Not too bad, how about you?""",
    extra_body={
        "response_format": "wav",
        "instructions": "Joe should sound firm, Jane should sound upbeat"
    }
)

conversation_response.stream_to_file("conversation.wav")

{
  "model": "gemini-2.5-flash-preview-tts",
  "input": "Say in a spooky whisper: By the pricking of my thumbs... Something wicked this way comes",
  "voice": "Enceladus",
  "response_format": "wav"
}

{
  "model": "gemini-2.5-flash-preview-tts",
  "input": "Speaker1: So... what's on the agenda today?\nSpeaker2: You're never going to guess!",
  "voice": "Kore",
  "response_format": "wav",
  "instructions": "Make Speaker1 sound tired and bored, and Speaker2 sound excited and happy"
}

{
  "model": "gemini-2.5-flash-preview-tts",
  "input": "Your transcript here",
  "voice": "Kore",
  "instructions": "# AUDIO PROFILE: Character Name\n## Role Description\n\n## THE SCENE: Scene Name\nDescribe the environment and mood\n\n### DIRECTOR'S NOTES\nStyle: Describe the style\nPacing: Describe the pacing\nAccent: Specify the accent"
}

{
  "error": {
    "message": "Error description",
    "type": "error_type",
    "code": "error_code"
  }
}

{
  "model": "gemini-2.5-flash-preview-tts",
  "input": "Speaker1: Hello!\nSpeaker2: Hi there!",
  "instructions": "Speaker1 should sound professional, Speaker2 should sound casual"
}