Model Tracker

AI models that generate speech and audio

Every model in the tracker that returns audio, as its maker describes it.

Every model in the tracker that returns audio, as its maker describes it.

• H3 Flex

  29 October 2026 · Generally available · Text, Image, Audio, Video · Video, Audio · Yes

• Amazon Nova 2.5 Sonic

  5 October 2026 · Generally available · Text, Audio · Text, Audio

• Gemini 3.8 Flash TTS

  23 September 2026 · Generally available · Text · Audio · 8,192 tokens · $0.50 per 1M tokens · $9.00 per 1M tokens

• Gemini 3.8 Flash-Lite TTS

  22 September 2026 · Generally available · Text · Audio · 8,192 tokens · $0.50 per 1M tokens · $6.00 per 1M tokens

• Grok Voice 2.0

  29 July 2026 · Deprecated · Text, Audio · Text, Audio

• Lyria 3.5

  29 July 2026 · Generally available · Text, Image · Audio, Text · 131,072 tokens

• GPT-Realtime-2.1

  6 July 2026 · Generally available · Text, Image, Audio · Text, Audio · 128,000 tokens · $4.00 per 1M tokens · $24.00 per 1M tokens

• GPT-Realtime-2.1 Mini

  6 July 2026 · Generally available · Text, Image, Audio · Text, Audio · 128,000 tokens · $0.60 text tokens · $2.40 text tokens

• Gemini 3.5 Live Translate

  9 June 2026 · Preview · Audio · Audio, Text

• GPT-Realtime-2

  7 May 2026 · Generally available · Text, Image, Audio · Text, Audio · 128,000 tokens

• GPT-Realtime-Translate

  7 May 2026 · Generally available · Audio · Text, Audio · 16,000 tokens

• Gemini 3.1 Flash Live

  26 March 2026 · Preview · Text, Image, Audio, Video · Text, Audio

• Lyria 3 Clip

  25 March 2026 · Preview · Text, Image · Audio, Text · 131,072 tokens

• Lyria 3 Pro

  25 March 2026 · Preview · Text, Image · Audio, Text · 131,072 tokens · $0.08 per song

• Voxtral TTS

  23 March 2026 · Generally available · Text, Audio · Audio · Yes

• GPT-Realtime-1.5

  23 February 2026 · Generally available · Text, Image, Audio · Text, Audio · 32,000 tokens

• Qwen3-TTS-12Hz-0.6B-Base

  22 January 2026 · Generally available · Text, Audio · Audio · Yes

• Qwen3-TTS-12Hz-0.6B-CustomVoice

  22 January 2026 · Generally available · Text · Audio · Yes

• Qwen3-TTS-12Hz-1.7B-Base

  22 January 2026 · Generally available · Text, Audio · Audio · Yes

• Qwen3-TTS-12Hz-1.7B-CustomVoice

  22 January 2026 · Generally available · Text · Audio · Yes

• Qwen3-TTS-12Hz-1.7B-VoiceDesign

  22 January 2026 · Generally available · Text · Audio · Yes

• SAM Audio

  16 December 2025 · Generally available · Text, Audio, Video · Audio · Yes

• Gemini 2.5 Flash Live

  12 December 2025 · Audio, Text

• Veo 3.1

  15 October 2025 · Video, Audio · 1,024 tokens

• GPT-Audio Mini

  6 October 2025 · Deprecated · Text, Audio · Text, Audio · 128,000 tokens · $0.60 per 1M tokens · $2.40 per 1M tokens

• Qwen3-Omni-30B-A3B-Instruct

  22 September 2025 · Generally available · Text, Image, Audio, Video · Text, Audio · Yes

• GPT-Realtime

  28 August 2025 · Deprecated · Text, Image, Audio · Text, Audio · 32,000 tokens

• Gemini 2.5 Flash TTS

  20 May 2025 · Text · Audio · 8,192 tokens · $0.50 per 1M tokens · $10.00 per 1M tokens

• Lyria RealTime

  20 May 2025 · Preview · Text · Audio

• Qwen2.5-Omni-3B

  30 April 2025 · Generally available · Text, Image, Audio, Video · Text, Audio · Yes

• Qwen2.5-Omni-7B

  26 March 2025 · Generally available · Text, Image, Audio, Video · Text, Audio · Yes

• GPT-4o Mini TTS

  20 March 2025 · Deprecated · Text · Audio · 2,000 tokens · $0.60 per 1M tokens · $12.00 per 1M tokens

• gpt-4o-mini-audio

  17 December 2024 · Deprecated · Text, Audio · Text, Audio · 128,000 tokens

• gpt-4o-audio

  17 October 2024 · Deprecated · Text, Audio · Text, Audio · 128,000 tokens

• gpt-4o-realtime

  1 October 2024 · Deprecated · Text, Audio · Text, Audio · 32,000 tokens

• SeamlessExpressive

  30 November 2023 · Generally available · Audio · Audio

• SeamlessM4T v2

  30 November 2023 · Generally available · Text, Audio · Text, Audio · Yes

• SeamlessStreaming

  30 November 2023 · Generally available · Audio · Text, Audio · Yes

• tts-1

  6 November 2023 · Deprecated · Text · Audio · 4,096 characters · $15.00 per 1000000 characters

• tts-1-hd

  6 November 2023 · Deprecated · Text · Audio · $30.00 per 1000000 characters

• SeamlessM4T

  22 August 2023 · Generally available · Text, Audio · Text, Audio · Yes

• AudioGen

  2 August 2023 · Generally available · Text · Audio · Yes

• MusicGen

  2 August 2023 · Generally available · Audio · Yes

• Voicebox

  16 June 2023 · Text, Audio · Audio · No

• Audiobox

  Text, Audio · Audio

• EnCodec

  Generally available · Audio · Audio · Yes

• Gemini 2.5 Pro TTS

  Text · Audio · 8,192 tokens · $1.00 per 1M tokens · $20.00 per 1M tokens

• Gemini 3.1 Flash TTS

  Text · Audio · 8,192 tokens · $1.00 per 1M tokens · $20.00 per 1M tokens

• Gemini 3.8 Live Extended Thinking

  Generally available · Text, Image, Audio, Video · Text, Audio · 128,000 tokens

• GPT-Audio

  Deprecated · Text, Audio · Text, Audio · 128,000 tokens

• GPT-Audio-1.5

  Generally available · Text, Audio · Text, Audio · 128,000 tokens

• GPT-Live 1

  Generally available · Text, Audio · Text, Audio · 128,000 tokens

• GPT-Realtime Mini

  Deprecated · Text, Image, Audio · Text, Audio · 32,000 tokens · $0.60 per 1M tokens · $2.40 per 1M tokens

• MAI-Voice-1

  Preview · Text · Audio

• Multi-Band Diffusion

  Generally available · Audio · Yes

Other lists

• Open-weight AI models
• AI models with a context window of 1 million tokens
• AI models that read images
• AI image generation models
• Retired and deprecated AI models

All of the Model Tracker