Remy Voice — Live Demo

Realtime

108 voices

One model listens, thinks, and speaks. Tap any voice to hear it.

Gemini 2.5 Flash Native AudioGoogle~$0.02 / min30 voices

Gemini 3.1 Flash LiveGoogle~$0.02 / min30 voices

GPT Realtime 2.1OpenAI~$0.30 / min10 voices

GPT Realtime 2.1 MiniOpenAI~$0.05 / min10 voices

Grok Voice (Think Fast 2.0)xAI$0.08 / min28 voices

Text-to-speech

131 voices

Standalone voices for narration, voiceover, or any app. Tap to hear.

Gemini 3.1 Flash TTSGoogle$1 / $20 per 1M tok30 voices

GPT-4o-mini TTSOpenAI$0.60 / $2.40 per 1M tok9 voices

Kokoro 82MKokoro$0.62 / 1M chars54 voices

Minimax Speech 2.8 HDMiniMax$0.007 / run17 voices

Orpheus 3BOrpheus$7 / 1M chars7 voices

Qwen Audio 3.0 TTS PlusQwen$27.59 / 1M chars2 voices

TTS-1OpenAI$15 / 1M chars6 voices

TTS HDOpenAI$30 / 1M chars6 voices

Also available · no preview clips

Cartesia Sonic 3Cartesiarealtime · low latency

Preview voices ~$37 / 1M chars

ElevenLabs TTSElevenLabsflagship · low latency

Preview voices ~$0.20 / 1k chars

Qwen3 TTSQwenopen source · multilingual

$20 / 1M chars

Speech-to-text

You can’t audition a transcription model. Here’s what each one costs.

Deepgram Nova-3Deepgramrealtime · low latency · accurate

$0.0058 / min

Scribe v1ElevenLabs

$0.0067 / min

Scribe v2ElevenLabslatest

$0.0067 / min

GPT TranscribeOpenAI

$2.50 / $10 per 1M tok

Qwen3 ASR 1.7BQwenopen source · multilingual

$0.00045 / min

Voxtral Mini 3BMistralopen source

$0.001 / min

Whisper-1OpenAIopen source · low cost · source audio

$0.006 / min

Whisper Large v3OpenAIopen source · low cost

$0.00045 / min

Whisper Large v3 TurboOpenAIopen source · fast · low cost

$0.0002 / min

Music

Generative music models, included for completeness. Priced per track.

ElevenLabs MusicElevenLabssource audio

$0.0058 / track

Lyria 3Googlemusic · latest

$0.04 / track

Lyria 3 ProGooglemusic · latest

$0.08 / track

MiniMax Music 2.5MiniMaxsource audio

$0.075 / song

MiniMax Music 3.0MiniMaxlatest · source audio

$0.15 / song