TTS models, split by track, ranked by preference.

# Hosted vendor API example shape
# Use your Gradium API key and selected voice ID from the dashboard.
import requests

resp = requests.post(
    "https://api.gradium.ai/v1/tts",
    headers={"Authorization": "Bearer $GRADIUM_API_KEY"},
    json={
        "voice": "russell",
        "text": "The quarterly revenue increased by 17.8 percent to 4.2 million dollars.",
        "format": "wav",
        "stream": True,
    },
    timeout=30,
)
resp.raise_for_status()
open("gradium.wav", "wb").write(resp.content)

# pip install kokoro>=0.8 soundfile
from kokoro import KPipeline
import soundfile as sf

pipe = KPipeline(lang_code="a")  # 'a' = American English
# Available voices: af_heart, af_bella, am_adam, am_michael, etc.
samples = pipe("Hello from Kokoro, the most efficient open-source TTS.", voice="af_heart", speed=1.0)
for i, (gs, ps, audio) in enumerate(samples):
    sf.write(f"output_{i}.wav", audio, 24000)

# pip install TTS
from TTS.api import TTS

tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=True)

# Zero-shot voice cloning from a 6s reference clip
tts.tts_to_file(
    text="This is a cloned voice speaking naturally.",
    speaker_wav="reference.wav",
    language="en",
    file_path="output.wav",
)

# pip install bark
from bark import SAMPLE_RATE, generate_audio, preload_models
from scipy.io.wavfile import write as write_wav

preload_models()

# Bark supports non-speech: laughter, music, hesitations
text = """Hello! [laughs] This is Bark speaking.
It can generate musical notes and even [sighs] emotions."""

audio = generate_audio(text, history_prompt="v2/en_speaker_6")
write_wav("output.wav", SAMPLE_RATE, audio)

# Install: pip install piper-tts
# Download a voice: piper --download-dir ./voices --model en_US-lessac-high
import subprocess

text = "Piper runs on a Raspberry Pi in real-time."
subprocess.run(
    ["piper", "--model", "./voices/en_US-lessac-high.onnx", "--output_file", "output.wav"],
    input=text.encode(),
)

# pip install fish-speech
from fish_speech.api import FishSpeechTTS

tts = FishSpeechTTS(device="cuda")

# Zero-shot cloning with 10-30s reference
tts.synthesize(
    text="Fish Speech excels at multilingual voice cloning.",
    reference_audio="speaker_ref.wav",
    output_path="output.wav",
)

# pip install diarizationlm  # Dia by Nari Labs
from dia import Dia

model = Dia("nari-labs/Dia-1.6B", device="cuda")

# Multi-speaker dialogue generation
dialogue = """[S1] Hey, have you tried the new open-source TTS models?
[S2] Yeah, Dia is amazing for dialogue. It handles turn-taking naturally.
[S1] The prosody between speakers is surprisingly good."""

audio = model.generate(dialogue)
model.save_audio("dialogue.wav", audio)

# pip install f5-tts
from f5_tts.api import F5TTS

tts = F5TTS(device="cuda")

# Zero-shot voice cloning via flow matching
tts.infer(
    ref_file="reference.wav",
    ref_text="This is the reference transcript.",
    gen_text="F5-TTS uses flow matching for natural-sounding speech synthesis.",
    output="output.wav",
)

# pip install parler-tts
from parler_tts import ParlerTTSForConditionalGeneration
from transformers import AutoTokenizer
import soundfile as sf

model = ParlerTTSForConditionalGeneration.from_pretrained("parler-tts/parler-tts-large-v1")
tokenizer = AutoTokenizer.from_pretrained("parler-tts/parler-tts-large-v1")

description = "A warm female voice with a slight British accent, speaking clearly and calmly."
prompt = "Parler TTS lets you describe the exact voice characteristics you want."

input_ids = tokenizer(description, return_tensors="pt").input_ids
prompt_ids = tokenizer(prompt, return_tensors="pt").input_ids

gen = model.generate(input_ids=input_ids, prompt_input_ids=prompt_ids)
sf.write("output.wav", gen.cpu().numpy().squeeze(), model.config.sampling_rate)