Speech synthesis with a published voice list, billed per character of input text.
Orpheus TTS is an open-source text-to-speech model from Canopy Labs, built on Llama 3.2 3B as a speech language model. It produces human-like speech with natural intonation, supports emotion control through simple tags and zero-shot voice cloning, and streams audio for real-time use.
Kokoro is an open-weight text-to-speech model from hexgrad with 82 million parameters, built on the StyleTTS 2 and ISTFTNet architectures. Released under Apache 2.0, it offers 54 voices across 8 languages and is designed to give natural speech while staying fast and inexpensive to run.
Qwen3-TTS 0.6B is the smaller text-to-speech model in Alibaba's Qwen team's Qwen3-TTS series, built on a multi-codebook language model with a 12Hz speech tokenizer. It speaks 10 languages including Chinese, English, Japanese and Spanish, supports streaming output, and balances quality with efficiency, with variants for preset voices and 3-second voice cloning.
Qwen3-TTS 1.7B is the larger text-to-speech model in Alibaba's Qwen team's Qwen3-TTS series, built on a multi-codebook language model with a 12Hz speech tokenizer. It speaks 10 languages including Chinese, English, Japanese and Spanish, supports streaming output and instruction-based style control, with variants for preset voices, voice design from a text description and 3-second voice cloning.
Chatterbox HD is a text-to-speech model from Resemble AI's Chatterbox family. The open-source Chatterbox models are built on a 0.5B Llama backbone and support zero-shot voice cloning from a short reference clip and control over emotional intensity, with a PerTh watermark in generated audio.
Eleven Turbo v2.5 is a low-latency text-to-speech model from ElevenLabs that generates speech in 32 languages. It is built for real-time and conversational uses where fast audio output matters more than maximum expressiveness.
Gemini 3.1 Flash TTS is Google's low-latency text-to-speech model that turns text into natural, expressive speech in more than 70 languages. It supports native multi-speaker dialogue and audio tags written into the text to steer style, pace and delivery, and its audio carries a SynthID watermark.
Gradium TTS is a real-time streaming text-to-speech model from Gradium, built for voice agents. It speaks English, French, German, Spanish and Portuguese with mid-sentence code-switching, works with instant and professional voice clones, and reads hard cases such as phone numbers and email addresses without separate text normalization.
Inworld TTS-1.5 Max is a text-to-speech model from Inworld AI for real-time, expressive voice applications. It speaks 15 languages, supports voice cloning from a sample, and is the higher-quality option in the TTS-1.5 family, alongside the lower-latency TTS-1.5 Mini.
Clone your voice from a short recording and generate natural speech in it across 30+ languages.
Grok Text to Speech is xAI's text-to-speech model for long-form and real-time speech generation. It offers built-in voices with distinct styles, speaks 20 languages, and uses inline and wrapping speech tags such as [laugh], [pause] and <whisper> to control delivery.
