Features

Audio / TTS Models (17 total)

Whisper — Speech-to-text transcription

TTS-1 — Text-to-speech optimized for speed

TTS-1 HD — Text-to-speech optimized for quality

Gemini 3.1 Flash TTS — Powerful, low-latency speech generation with expressive audio tags for precise narration control — 70+ languages

Google TTS Standard — Google Cloud Text-to-Speech — standard voices, 40+ languages

Google TTS Neural2 — Google Neural2 voices — highly natural-sounding TTS using novel synthesis methods

Google Chirp3 HD — Google's most expressive TTS — Chirp3 HD voices with studio-quality audio

Google TTS Studio — Google Studio voices — highest quality, human-like expressiveness

ElevenLabs TTS — ElevenLabs Eleven v3 — ultra-realistic voice synthesis with 30+ languages and voice cloning

ElevenLabs Flash — ElevenLabs Flash v2.5 — lowest latency TTS for real-time applications, 32 languages

Qwen3 TTS Flash — Alibaba's multilingual TTS with 49 voices, 10+ languages - ElevenLabs alternative

Qwen3 TTS Flash (Nov 2025) — Snapshot version of Qwen3 TTS Flash with 49 voices

Qwen3 TTS Instruct Flash — Instruction-controllable TTS - control speech style via text instructions, 10+ languages

Qwen3 TTS Voice Design — Generate custom voices from text descriptions - design unique voices without audio samples

Qwen3 TTS Voice Clone — Clone voices from 10-20 second audio samples - highly natural voice replication

CosyVoice V3 Plus — Next-gen generative TTS model - high-quality real-time streaming synthesis

CosyVoice V3 Flash — Fast CosyVoice TTS - cost-effective streaming synthesis

How to use: Go to the Audio page for text-to-speech, transcription, and voice features.

Need more help with this topic?