Try PixVerse C1 Reference-to-Video Model from PixVerse →
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Speech to Speech models

Speech to speech models and APIs.

Audio in, audio out: change or convert a voice, translate speech, or hold a spoken conversation with a live voice model.

Showing 16 of 16 models
gemini 3.8 live - AI model cover image

gemini 3.8 live

google

Google Gemini 3.8 Live is a low-latency audio model for voice agents. It streams natural 24 kHz speech, supports tool calling, and optional Search grounding.

Speech to Speech
Run
gpt-live-1 - AI model cover image

gpt-live-1

openai

GPT‑Live‑1 is OpenAI’s full‑duplex voice model for real-time conversation. It streams speech and transcripts and can delegate reasoning and tools to a backend model.

Speech to Speech
Run
speech-to-speech-v2 - AI model cover image

speech-to-speech-v2

elevenlabs

Re-voice an existing recording with a chosen ElevenLabs voice while keeping the original words, timing, and delivery. Export MP3 in common 22.05 kHz and 44.1 kHz presets.

Speech to Speechelevenlabs
Run
gpt-realtime-translate - AI model cover image

gpt-realtime-translate

openai

Stream live speech and get translated speech plus live captions with low delay. Made by OpenAI for calls, meetings, broadcasts, and video chat translation.

Speech to Speech
Run
gpt-realtime-2.1-mini - AI model cover image

gpt-realtime-2.1-mini

openai

Build low-latency voice agents with OpenAI’s GPT‑Realtime 2.1 Mini. It takes live audio or text and replies with spoken audio plus a transcript. ([developers.openai.com](https://developers.openai.com/api/docs/models/gpt-realtime-2.1-mini))

Speech to Speech
Run
gpt-realtime-2.1 - AI model cover image

gpt-realtime-2.1

openai

OpenAI's GPT Realtime 2.1 runs speech-to-speech conversations with configurable reasoning and tool calls. It’s built for voice agents that handle noise and interruptions.

Speech to Speech
Run
chatterbox-turbo - AI model cover image

chatterbox-turbo

resemble-ai

The fastest open source TTS model without sacrificing quality.

Speech to Speechspeech-to-textspeech-to-speech
Run
chatterbox-multilingual - AI model cover image

chatterbox-multilingual

resemble-ai

Generate expressive, natural speech in 23 languages. Features instant voice cloning from short audio, emotion control, and seamless cross-language voice transfer.

Speech to Speechspeech-to-textspeech-to-speech
Run
Realtime Conversational AI - AI model cover image

Realtime Conversational AI

elevenlabs

A real-time voice conversation tool using ElevenLabs' AI voice agents. Customize voices, behaviors, and languages for interactive AI experiences.

Speech to Speech
Run
gpt-realtime-mini - AI model cover image

gpt-realtime-mini

openai

GPT Mini Realtime enables low-latency, bidirectional streaming for voice and text. Build interactive, responsive AI experiences that feel natural and immediate.

Speech to Speech
Run
gpt-realtime - AI model cover image

gpt-realtime

openai

GPT Realtime enables low-latency, bidirectional streaming for voice and text. Build interactive, responsive AI experiences that feel natural and immediate.

Speech to Speech
Run
PersonaPlex-Realtime - AI model cover image

PersonaPlex-Realtime

nvidia

Convert speech to speech with customizable voices using PersonaPlex. Supports various audio formats and offers control over text temperature and audio top K settings.

Speech to Speechspeech-to-textaudio
Run
VoxCPM - AI model cover image

VoxCPM

openbmb

Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning

Speech to Speechspeech-to-textspeech-to-speech
Run
RVC-Voice-Clone-Youtube - AI model cover image

RVC-Voice-Clone-Youtube

wiro

Clone any voice and cover any YouTube song with it. This tool lets you apply a custom-trained RVC voice model to recreate any YouTube song in that voice.

Speech to Speechvoice clonerealistic voice
Run
voice-clone - AI model cover image

voice-clone

wiro

A text-to-speech tool by Coqui that generates natural-sounding speech from text and performs voice cloning by taking a 6-second voice sample to produce new voice outputs.

Speech to Speech
Run
noise-reduction - AI model cover image

noise-reduction

librosa

Noise reduction algorithm that reduces noise in time-domain signals like speech, bioacoustics, and physiological signals.

Speech to Speechlibrosaaudio
Run

How to pick a speech to speech model

Speech to speech takes audio in and gives audio back. That covers three different jobs: changing a voice, translating speech, and holding a live conversation.

Translation

GPT Realtime Translate turns live speech into translated speech plus captions, for calls, meetings and broadcasts.

Clean up audio

Noise Reduction removes background noise from speech before you transcribe or re-voice it.

Frequently asked questions

What is the difference between changing a voice and cloning one?

A voice changer keeps your recording and swaps the voice. A cloning model learns a voice from a short sample and then reads new text with it. Cloning models are in voice cloning.

How are realtime models billed?

Per conversation turn, taken from your credits while the session runs. Jobs on recorded audio are billed per run or by length, as each model page shows.

Do I need a WebSocket?

For live conversations, yes. You start the session with a normal API call, then stream audio over a WebSocket. Recorded files work like any other model run.