Text to speech models and APIs.

Google’s Gemini 3.8 Flash TTS generates studio-grade speech from text, with inline vocal tags, style direction, and optional two-speaker dialogue in 130+ languages.

Generate high-fidelity sound effects from a text description with ElevenLabs Sound Effects v3. Built for games, video edits, Foley, and ambient loops.

Generate expressive speech from text with MiMo 2.5 TTS by XiaomiMiMo. Use preset voices, design a new voice, or clone a voice from audio.

EMA Lightning turns Turkish text into speech and can stream mono WAV audio up to 48 kHz. Adjust speaking speed and set a seed for repeatable takes.

Turn a scripted conversation into expressive speech with ElevenLabs Eleven v4 Turbo. Provide a multi-voice dialogue JSON and get a single MP3 scene.

Generate natural multi-speaker dialogue with ElevenLabs Eleven v4. Provide a turn-by-turn script and receive a single MP3 track with expressive delivery cues.

Eleven V4 Turbo by ElevenLabs turns tagged scripts into expressive speech audio for real-time apps. Choose a voice, tune delivery settings, and export MP3.

Eleven V4 by ElevenLabs turns scripts into emotionally rich speech with strong speaker identity and multilingual coverage. Add audio tags and export MP3 audio.

Generate natural speech from text with Gemini 3.1 Flash TTS. Use voice options and expressive tags to control tone and pacing for narration, apps, and accessibility.

OpenMOSS MOSS-TTS v1.5 turns text into natural speech, with optional zero-shot voice cloning from a reference clip. It supports 31 languages plus pause and pronunciation control.

Multilingual text-to-speech from OpenBMB: 2B parameters, 30 languages, 48 kHz output. Clone a voice from a short clip or describe a new one in words, with audio streamed back as it is generated.

OmniVoice by k2-fsa generates 24 kHz speech from text in 600+ languages. Clone a speaker from a short reference clip or design a new voice from attributes.

Multilingual text-to-speech from Hume AI that clones a voice from a reference clip, built on Llama 3.2 3B. Its tokenizer pairs each text token with one acoustic vector, which keeps the audio aligned to the script.

Generates high-quality speech from text using advanced TTS technology with support for voice cloning and multi-speaker synthesis.

Generates natural-sounding speech from text with support for multi-speaker voice cloning and fast inference capabilities.

Open-source English TTS model from Resemble AI, a lighter 350M-parameter Chatterbox variant. Clones a voice from a short clip and performs inline tags like [laugh], [chuckle] and [cough].

Generate expressive speech in 23 languages with zero-shot voice cloning from a short reference clip, an emotion exaggeration control and cross-language voice transfer.

OpenMOSS's 8B dialogue model turns a speaker-tagged script into one audio track with up to five voices, each of which can be cloned from a 3 to 10 second clip.

Streaming text-to-speech from OpenMOSS that sends audio in chunks while the rest of the text is still being synthesized. Clones a voice from one reference clip and speaks 20 languages.

Qwen's 1.7B-parameter text-to-speech model with nine preset voices across 10 languages. A short written instruction sets the emotion and pace of each line.