“text to speech”

Text-to-speech (TTS) with Next-gen Kaldi

Text-to-speech client demo from the Transformers.js author.

Russian text-to-speech.

Synthesises speech from text with Microsoft Edge voices, adjustable for rate and pitch.

Converts text to speech in the browser with the Kokoro model.

Free text-to-speech tool with voice choices and emotion control for the spoken output.

Reads text aloud with Google Gemini speech voices, with a voice picker and audio download.

Reads text aloud with a speech model executed in the browser through Gradio-Lite.

Reads text aloud with ElevenLabs voices, with language and speed controls.

Converts text to speech with the Kokoro model, running in your browser via WebGPU.

Reads Ukrainian text aloud with a multispeaker StyleTTS2 voice.

Turns text into speech with MeloTTS, a multilingual text-to-speech model.

Free text-to-speech site with a large voice list across many languages; the page says no sign-up is needed.

Turns text into speech with the Kitten TTS 2 model and the open-source 0.8 models.

Generates natural-sounding conversational speech from text with Sesame's CSM-1B model.

Voice typing page that turns speech into text as you talk, and can also transcribe uploaded recordings.

Transcribes speech to text in real time using the Whisper large turbo model.

Converts text to speech with the Fish Audio S2 Pro model on ZeroGPU.

Text-to-speech app built on the Orpheus TTS model that turns typed text into spoken audio.

Anime-character style Japanese text-to-speech with many speaker voices.

Converts text to speech with Chatterbox, which supports 23 languages.

Spanish text-to-speech using Piper voices.

WebAssembly build of whisper.cpp that transcribes microphone or file audio inside the browser.

Turns text into natural speech with the 82M-parameter Kokoro model and several voices.