/audio/speech

Overview

Feature	Supported	Notes
Cost Tracking	✅	Works with all supported models
Logging	✅	Works across all integrations
Fallbacks	✅	Works between supported models
Loadbalancing	✅	Works between supported models
Supported Providers	OpenAI, Azure OpenAI, Vertex AI, AWS Polly, ElevenLabs, MiniMax

Quick Start

Python

from pathlib import Path
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

speech_file_path = Path(__file__).parent / "speech.mp3"

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

response.stream_to_file(speech_file_path)

cURL

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

Using Different Models

OpenAI TTS

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.audio.speech.create(
    model="openai/tts-1",
    voice="alloy",  # Options: alloy, echo, fable, onyx, nova, shimmer
    input="Hello, this is a test of text to speech."
)

response.stream_to_file("speech.mp3")

OpenAI TTS HD

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.audio.speech.create(
    model="openai/tts-1-hd",
    voice="nova",
    input="This is high-definition text to speech."
)

response.stream_to_file("speech_hd.mp3")

Gemini TTS

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.haimaker.ai/v1"
)

response = client.audio.speech.create(
    model="gemini/gemini-2.5-flash-preview-tts",
    voice="alloy",
    input="The quick brown fox jumped over the lazy dogs"
)

response.stream_to_file("gemini_speech.mp3")

Available Voices

For OpenAI TTS models, the available voices are:

Voice	Description
alloy	Neutral, balanced voice
echo	Warm, conversational voice
fable	Expressive, storytelling voice
onyx	Deep, authoritative voice
nova	Friendly, upbeat voice
shimmer	Clear, professional voice

Supported Providers

Provider	Documentation Link
OpenAI	Usage
Azure OpenAI	Azure TTS
Vertex AI	Vertex AI TTS
ElevenLabs	ElevenLabs TTS
MiniMax	MiniMax TTS