MODELS
Leading Speech Models
Compare speech recognition, text-to-speech, realtime voice, audio modalities, and provider APIs.
18 of 18 model versions
| Model | Family | Organization | Providers | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Price | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Seedance 2.5 bytedance-seed/seedance-2-5 | BSBytedance Seed | Seed | - | - | - | -No | -No | -No | -No | Closed | Pricing unavailable | 2026-07-31 | 2026-09-10 | |||
| GPT-Realtime-2.1 openai/gpt-realtime-2.1 | OPOpenAI | GPT | 128K | 32K | Yes | Yes | -No | -No | Closed | input $4/M · output $24/M cache read $0.4/M | 2026-07-06 | 2026-07-06 | ||||
| Gemini 3.5 Live Translate Preview google/gemini-3.5-live-translate-preview | GOGoogle | Gemini | 131K | 66K | -No | -No | -No | -No | Closed | input $3.5/M · output $21/M | 2026-06-09 | 2026-06-09 | ||||
| Gemini 3.1 Flash TTS Preview google/gemini-3.1-flash-tts-preview | GOGoogle | Gemini | 8.2K | 16K | -No | -No | -No | Yes | Closed | input $1/M · output $20/M | 2026-04-15 | 2026-04-15 | ||||
| Gemini 3.1 Flash Live Preview google/gemini-3.1-flash-live-preview | GOGoogle | Gemini | 131K | 66K | Yes | Yes | -No | Yes | Closed | input $0.75/M · output $4.5/M | 2026-03-26 | 2026-03-26 | ||||
| Lyria 3 Clip Preview google/lyria-3-clip-preview | GOGoogle | Lyria | 131K | 66K | -No | -No | -No | Yes | Closed | input $0/M · output $0/M | 2026-03-25 | 2026-03-25 | ||||
| Lyria 3 Pro Preview google/lyria-3-pro-preview | GOGoogle | Lyria | 131K | 8.2K | -No | -No | -No | Yes | Closed | input $0/M · output $0/M | 2026-03-25 | 2026-03-25 | ||||
| Seedance 2.0 bytedance-seed/seedance-2-0 | BSBytedance Seed | Seed | - | - | - | -No | -No | -No | -No | Closed | Pricing unavailable | 2026-02-12 | 2026-09-10 | |||
| Kling Video 3.0 kuaishou/kling-video-3-0 | KUKuaishou | Kling Video | - | - | - | -No | -No | -No | -No | Closed | Pricing unavailable | 2026-02-05 | 2026-09-10 | |||
| Kling Video 3.0 Omni kuaishou/kling-video-3-0-omni | KUKuaishou | Kling Video | - | - | - | -No | -No | -No | -No | Closed | Pricing unavailable | 2026-02-05 | 2026-09-10 | |||
| gpt-audio openai/gpt-audio | OPOpenAI | GPT | 128K | 16K | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-01-19 | 2026-08-06 | ||||
| gpt-audio-mini openai/gpt-audio-mini | OPOpenAI | GPT | 128K | 16K | -No | Yes | Yes | Yes | Closed | Pricing unavailable | 2026-01-19 | 2026-08-06 | ||||
| Seedance 1.5 Pro bytedance-seed/seedance-1-5-pro | BSBytedance Seed | Seed | - | - | - | -No | -No | -No | -No | Closed | Pricing unavailable | 2025-12-15 | 2026-09-10 | |||
| Sora 2 openai/sora-2 | OPOpenAI | Sora | - | - | -No | -No | -No | -No | Closed | Pricing unavailable | 2025-10-06 | 2026-09-10 | ||||
| Sora 2 Pro openai/sora-2-pro | OPOpenAI | Sora | - | - | -No | -No | -No | -No | Closed | Pricing unavailable | 2025-10-06 | 2026-09-10 | ||||
| Gemini 2.5 Flash TTS google/gemini-2.5-flash-preview-tts | GOGoogle | Gemini | 33K | 16K | -No | -No | -No | Yes | Closed | Pricing unavailable | 2025-09-30 | 2026-08-06 | ||||
| Gemini 2.5 Pro TTS google/gemini-2.5-pro-preview-tts | GOGoogle | Gemini | 33K | 16K | -No | -No | -No | -No | Closed | Pricing unavailable | 2025-09-30 | 2026-08-06 | ||||
| Qwen-Omni Turbo alibaba/qwen-omni-turbo | ALAlibaba | Qwen | 33K | 2K | -No | Yes | -No | Yes | Closed | input $0.07/M · output $0.27/M | 2025-01-19 | 2025-03-26 |