Gandr

Unlimited text-to-speech and instant voice cloning — flat per concurrent stream

Paid - Flat billing per concurrent stream (unlimited characters/usage per stream). No per-character meter and no per-voice fees; clones cached after first use.

Visit Website

About Gandr

Gandr provides unlimited text-to-speech and instant voice cloning billed as a flat fee per concurrent stream (no per-character meter). Deliver real-time, streaming-first audio (server-side p50 ~116 ms), clone a voice from ~10s of reference audio (cached after first use), and output in 23 languages. Integrates via WebSocket and HTTP for agents, narration, dubbing, audiobooks, games, podcasts and voice agents. Single endpoint with redundant serving tiers and signed audio delivery.

Key Features

Unlimited TTS with flat per-concurrent-stream pricing (no per-character fees)
Instant voice cloning from ~10s reference audio, cached after first use
Streaming-first, low-latency audio (server-side p50 ≈116 ms; ~146 ms first byte over internet)
Supports 23 languages and multi-language voices
Integrates via WebSocket and HTTP with a single redundant endpoint

Who is this for?

Developers and teams building voice-enabled products (audiobooks, dubbing, e-learning, games, podcasts, conversational agents)

Comments (0)

No comments yet

Be the first to share your thoughts!

Stats

Upvotes6

Comments0

Pricing

Paid

Flat billing per concurrent stream (unlimited characters/usage per stream). No per-character meter and no per-voice fees; clones cached after first use.