TTS-1 HD is OpenAI's text-to-speech model optimized for high quality audio, converting text to natural sounding spoken audio.
Any
Any
TTS-1 HD is OpenAI's text-to-speech model optimized for high quality audio, converting text to natural sounding spoken audio.
TTS-1 is OpenAI's text-to-speech model optimized for real-time, low-latency use, converting text to natural sounding spoken audio.
Qwen3-TTS 1.7B is the larger 1.7B-parameter model of the Qwen3-TTS family, adding natural-language instruction control over timbre, emotion, and prosody on top of 9 preset voices covering various combinations of gender, age, language, and dialect. Qwen3-TTS is a family of multilingual, controllable, streaming text-to-s…
Qwen3-TTS 0.6B is the lightweight 0.6B-parameter model of the Qwen3-TTS family, with 9 preset voices covering various combinations of gender, age, language, and dialect, at a lower cost than the 1.7B model. The family consists of multilingual streaming text-to-speech models trained on over 5 million hours of speech in…
Dia is a 1.6B parameter text to speech model created by Nari Labs. Dia directly generates highly realistic dialogue from a transcript. You can condition the output on audio, enabling emotion and tone control. The model can also produce nonverbal communications like laughter, coughing, clearing throat, etc.
Chatterbox Multilingual is the multilingual general-purpose model in Chatterbox, Resemble AI’s open-source text-to-speech family.
Generate expressive, natural speech with Resemble AI's Chatterbox HD. Features unique emotion control, instant voice cloning from short audio, and built-in watermarking.
Chatterbox is a family of open-source text-to-speech models from Resemble AI.
MiniMax Speech 2.8 Turbo is the fast tier of MiniMax Speech 2.8, combining low latency with natural flow across 40 languages and 7 emotions at a lower cost than HD. MiniMax Speech 2.8 introduces native sound tag support, high-fidelity cloning, and studio-grade clarity, closing the gap between AI and the human voice.
MiniMax Speech 2.8 HD is the high-definition tier of MiniMax Speech 2.8, tuned for realistic quality with sound tags across 40 languages and 7 emotions. MiniMax Speech 2.8 introduces native sound tag support, high-fidelity cloning, and studio-grade clarity, closing the gap between AI and the human voice.
MiniMax Speech 2.6 Turbo is the fast, cost-efficient tier of MiniMax Speech 2.6, built for the best value and low latency across 40 languages. MiniMax Speech 2.6 brings comprehensive upgrades with ultra-low latency, enhanced format handling, and a more natural, human-like voice for Voice Agent scenarios.
MiniMax Speech 2.6 HD is the high-definition tier of MiniMax Speech 2.6, built for the highest voice similarity and ultra-high audio quality across 40 languages. MiniMax Speech 2.6 brings comprehensive upgrades with ultra-low latency, enhanced format handling, and a more natural, human-like voice for Voice Agent scenar…
MiniMax Speech 02 Turbo is the fast tier of MiniMax Speech 02, tuned for rhythm and stability with low latency at a lower cost than HD. MiniMax Speech 02 is a high-quality TTS system based on an AR Transformer architecture, supporting 32 languages across a wide range of accents and emotional expressions.
MiniMax Speech 02 HD is the high-definition tier of MiniMax Speech 02, with stronger voice replication similarity and high-quality voice generation; it is the variant that ranked first on the Artificial Analysis Speech Arena and the Hugging Face TTS Arena. MiniMax Speech 02 is a high-quality TTS system based on an AR T…
TTS 2.0 presents Query-Response mechanism that brings the next generation of speech technologies. It can synchronously understand both Query and Response texts, greatly expanding the scope of contextual comprehension and significantly enhancing the anthropomorphism and emotional expression in conversations.
Orpheus TTS is a SOTA open-source text-to-speech system built on the Llama-3b backbone. Orpheus demonstrates the emergent capabilities of using LLMs for speech synthesis.
HeyGen Voice Turbo is a lower-latency version of HeyGen Voice, HeyGen's in-house text-to-speech model, and heygen-voice-1-turbo is its faster speech generation tier. Use a public voice or create a clone from a recording; public voices and clones use the same speech endpoints. It has the same 10 default voices and strea…
HeyGen Voice is HeyGen's in-house text-to-speech model, and heygen-voice-1 is its standard speech generation tier. Use a public voice or create a clone from a recording; public voices and clones use the same speech endpoints. It comes with 10 default voices and streams 44.1 kHz mono PCM audio, with support for 39 langu…
Convert text into spoken audio with a single API call. The API supports a rich set of expressive voices, inline speech tags for fine-grained delivery control, and output formats from high-fidelity MP3 to telephony-optimized μ-law.
Eleven v4 Turbo is ElevenLabs’ low-latency model for real-time speech synthesis, with a median latency of ~100 ms. It keeps Eleven v4's expressive delivery and audio tags while being tuned for faster generation. It supports high-fidelity voice cloning and 90+ languages, and has a 10,000-character request limit.
Voxtral Mini TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, and supports zero-shot and professional voice cloning. It supports 35+ languages and 50+ dialects, streaming with ~90 ms time-to-first-audio, 5 output formats, and 34 emotion tags and…
Gemini 3.8 Flash TTS is Google's flagship creative text-to-speech model, engineered for studio-grade voice fidelity, expressive acting, authentic regional accents, and rock-solid long-form multi-turn stability.
Gemini 3.8 Flash-Lite TTS is Google's fast, cost-efficient workhorse text-to-speech model built to replace Gemini 3.1 Flash TTS Preview for high-throughput production workloads.
Eleven v4 is a speech synthesis model from ElevenLabs and its highest-quality, most expressive option, with inline audio tags for emotional and delivery control over how voices are performed. It supports 90+ languages and has a 10,000-character request limit, and offers high-fidelity voice cloning that keeps the speake…
Eleven Flash v2.5 is an ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time use cases, supports 32 languages, and has a 40,000-character request limit.
Eleven Flash v2 is an English-only, ultra-low-latency text-to-speech model from ElevenLabs. It is suited for conversational and real-time English use cases, and has a 30,000-character request limit.
Eleven-Multilingual-v2 is ElevenLabs’ most advanced multilingual text-to-speech model, delivering high-quality voice synthesis across a wide range of languages with improved realism and expressiveness. It is optimized for both accuracy and naturalness in multilingual scenarios.
A text-to-speech model from OpenAI built on GPT-4o mini, a fast language model. Use it to convert text into natural-sounding spoken audio.
Eleven-v3 is ElevenLabs’ most expressive text-to-speech model, supporting over 70 languages, multi-speaker dialogue, and advanced audio tags such as [excited], [whispers], [laughs], and [sighs]. It gives fine control over delivery, enabling dynamic, context-aware conversations with improved expressiveness and fine-grai…
Eleven-Turbo-v2 is an English-optimized TTS model from ElevenLabs, designed for fast, high-quality speech synthesis with low latency. It is ideal for real-time applications and interactive voice systems.
Eleven-Multilingual-v2 is ElevenLabs’ most advanced multilingual text-to-speech model, delivering high-quality voice synthesis across a wide range of languages with improved realism and expressiveness. It is optimized for both accuracy and naturalness in multilingual scenarios.
A text-to-speech model from OpenAI built on GPT-4o mini, a fast language model. Use it to convert text into natural-sounding spoken audio.
