Voice · Gradium

Gradium TTS

A voice model from Gradium built for accurate pronunciation and low latency. Pick it for tricky names and terms read clearly.

Anonymized High cost
Latest versionGradium TTSAugust 2026
Artificial Analysis Speech Arena1,151 Elo#5 of 10 on Artificial Analysis Speech Arena
Price$0.0214 per 1,000 characters$0.0641 a page read aloud

What sets it apart

Gradium TTS is built for real-time voice agents, with a first audio chunk in under 50 ms and attention to hard cases like phone numbers and alphanumeric text. It is a young model, first seen on the Artificial Analysis arena in August 2026.

  • Under 50 ms to first audio
  • Strong on phone numbers and codes
  • Cloud or on-device options

Strengths and limits

Where it shines

  • Gradium reports strong results on hard-to-pronounce sentences
  • 12 voices

Think twice when

  • Mid-range price per character
  • Anonymized, not private
  • 12 voices
  • Up to 5,000 characters per request in Sub Rosa

Use cases

Spelling out a phone number

Read this aloud clearly: call 04 78 22 31 90, reference AB-7731-QX.

Built for alphanumeric text.

Voice agent replies

Your order has shipped and will arrive on Thursday.

Very low latency.

Against its rivals

  • ElevenLabsElevenLabs has a longer track record and more languages, with a lower arena score here.#1 of 10 on Artificial Analysis Speech Arena (1,330 Elo)
  • Inworld TTS-1.5 MaxInworld is cheaper and also aimed at real time.
  • MiniMax Speech-02 HDMiniMax Speech-02 HD has more languages, with a lower arena score.#6 of 10 on Artificial Analysis Speech Arena (1,114 Elo)
Compare side by side ↗

Version history

Each version, dated, with what it changed over the one before.

  1. Gradium TTSLatest
    • Introduced a real-time TTS model aimed at voice agents, with voice cloning and voice design
    Source : artificialanalysis.ai

Benchmarks

How to read these scores: what a benchmark tells you.

Artificial Analysis Speech Arena: #5 of 10 models measured in the catalog. People listen to the same sentence read by two voices, without knowing the models, and pick the more natural one. An Elo rating: higher sounds more natural to more people. 100 points apart means the higher-rated model wins about 64% of duels.

Artificial Analysis Speech ArenaElo rating · Artificial Analysis, October 4, 2026
  1. 1. ElevenLabs TTS v4 TurboElevenLabs1,330
  2. 2. ElevenLabs TTS v4ElevenLabs1,329
  3. 3. Gemini 3.1 Flash TTSGemini 3.1 Flash TTS1,209
  4. 4. ElevenLabs TTS v3ElevenLabs1,178
  5. 5. Gradium TTSGradium TTS1,151
  6. 6. MiniMax Speech-02 HDMiniMax Speech-02 HD1,114
  7. 7. Chatterbox HD (Resemble AI)Chatterbox HD1,102
  8. 8. ElevenLabs Turbo v2.5ElevenLabs1,097
  9. 9. ElevenLabs Multilingual v2ElevenLabs1,095
  10. 10. Kokoro Text to SpeechKokoro1,064
See the numbers
ModelElo
1. ElevenLabs TTS v4 Turbo1,330
2. ElevenLabs TTS v41,329
3. Gemini 3.1 Flash TTS1,209
4. ElevenLabs TTS v31,178
5. Gradium TTS1,151
6. MiniMax Speech-02 HD1,114
7. Chatterbox HD (Resemble AI)1,102
8. ElevenLabs Turbo v2.51,097
9. ElevenLabs Multilingual v21,095
10. Kokoro Text to Speech1,064

The model in this family

ModelUsePrivacyPrice
Gradium TTStts-gradium-v1VoiceAnonymized$0.0214 per 1,000 characters$0.0641 a page read aloud

Specifications

SpecificationGradium TTS
ReleasedAugust 2026
Acceptstext
Producesaudio
Price$0.0214 per 1,000 characters
PrivacyAnonymized

Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.

Sources

Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.

Show the 3 sources
Learn more about Gradium TTS ↗