HomeSpeech-to-speech

Realtime streaming speech-to-speech models

59 speech-to-speech models from 16 providers stream audio back as it is generated over a WebSocket or WebRTC connection, for live captions, calls and voice agents.

The cheapest published USD price is Speech Realtime DeepSeek V4 Flash from Yandex SpeechKit at $0.78 per hour; 13 of 59 have a comparable price.

Of these, 6 have an announced shutdown date.

Prices are normalized: USD per hour of audio, cheapest first. Tick models to compare them side by side, or refine these filters.

59 matches

Speech-to-text and realtime $ per hour of audio, log scale 239 priced, 277 without a USD price

Speech-to-text and realtime: 239 models with a published USD price per hour of audio, from $0.05 to $20 and beyond, shown on a log scale.

other models matches your filtersAll models by price

Compare Model Provider Type Langs Features Price ↑ Status
speech-realtime-deepseek-v4-flashSpeech Realtime DeepSeek V4 FlashYandex SpeechKit, S2S, alpha Yandex SpeechKit S2S 2 0/19 $0.78 per hour Alpha
speech-realtime-max-tts-liveSpeech Realtime Max TTS LiveYandex SpeechKit, S2S Yandex SpeechKit S2S 2 0/19 $0.78 per hour Default
gpt-realtime-translateGPT-Realtime-TranslateOpenAI, S2S OpenAI S2S – 0/19 $2.04 per hour
ultravox-v0.6Ultravox v0.6 (Llama 3.3 70B)Inworld AI, S2S Inworld AI S2S 26 0/19 $3.00 per hour
ultravox-v0.6-gemma3-27bUltravox v0.6 (Gemma 3 27B)Inworld AI, S2S Inworld AI S2S 26 0/19 $3.00 per hour
ultravox-v0.7Ultravox v0.7 (GLM 4.6)Inworld AI, S2S Inworld AI S2S 26 0/19 $3.00 per hour Default
gpt-live-1GPT-Live 1OpenAI, S2S OpenAI S2S – 0/19 $3.00 per hour Default
gpt-live-1.1GPT-Live-1.1OpenAI, S2S OpenAI S2S – 0/19 $3.00 per hour
phonic-1Phonic-1Phonic, S2S Phonic S2S 52 0/19 $4.20 per hour Default
eleven_realtime_v1_maxEleven Realtime v1 MaxElevenLabs, S2S ElevenLabs S2S Many 0/19 $4.80 per hour
eleven_realtime_v1_miniEleven Realtime v1 MiniElevenLabs, S2S ElevenLabs S2S Many 0/19 $4.80 per hour
grok-voice-3.0Grok Voice 3.0xAI, S2S xAI S2S 16 3/19 $4.80 per hour Default
grok-voice-latestGrok Voice (latest)xAI, S2S xAI S2S 16 3/19 $4.80 per hour
qwen-audio-3.0-realtime-flashQwen-Audio 3.0 Realtime FlashAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 13 0/19 $0.23 per 1M tokens
qwen-audio-3.0-realtime-plusQwen-Audio 3.0 Realtime PlusAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 13 0/19 $0.80 per 1M tokens
qwen-audio-3.1-realtime-flashQwen-Audio 3.1 Realtime FlashAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 16 0/19 $0.23 per 1M tokens
qwen-audio-3.1-realtime-plusQwen-Audio 3.1 Realtime PlusAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 16 0/19 $0.80 per 1M tokens
qwen3-omni-flash-realtime-2025-09-15Qwen3-Omni Flash Realtime (2025-09-15)Alibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 14 0/19 $0.52 per 1M tokens
qwen3.5-livetranslate-flash-realtimeQwen3.5-LiveTranslate Flash RealtimeAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 61 0/19 $7.50 per 1M tokens
qwen3.5-livetranslate-flash-realtime-2026-05-19Qwen3.5-LiveTranslate Flash Realtime (2026-05-19)Alibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 61 0/19 $7.50 per 1M tokens
qwen3.5-omni-flash-realtimeQwen3.5-Omni Flash RealtimeAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 31 0/19 $0.55 per 1M tokens
qwen3.5-omni-flash-realtime-2026-03-15Qwen3.5-Omni Flash Realtime (2026-03-15)Alibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 31 0/19 $0.55 per 1M tokens
qwen3.5-omni-plus-realtimeQwen3.5-Omni Plus RealtimeAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 31 0/19 $2.10 per 1M tokens
qwen3.5-omni-plus-realtime-2026-03-15Qwen3.5-Omni Plus Realtime (2026-03-15)Alibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 31 0/19 $2.10 per 1M tokens
qwen3.8-livetranslate-flash-realtimeQwen3.8-LiveTranslate Flash RealtimeAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 61 0/19 $7.50 per 1M tokens
qwen3.8-omni-flash-realtimeQwen3.8-Omni Flash RealtimeAlibaba Cloud Model Studio, S2S Alibaba Cloud Model Studio S2S 31 0/19 $0.23 per 1M tokens Default
voice-live-liteVoice Live LiteAzure Speech, S2S Azure Speech S2S Many 0/19 $15.00 per 1M tokens
voice-live-proVoice Live ProAzure Speech, S2S Azure Speech S2S Many 0/19 $17.00 per 1M tokens Default
voice-live-standardVoice Live StandardAzure Speech, S2S Azure Speech S2S Many 0/19 $15.00 per 1M tokens
audio-mini-realtime-farSpeech-Language LLM Lite (far-field)Baidu AI Cloud Speech, S2S Baidu AI Cloud Speech S2S – 0/19 ¥16.00 per 1M tokens
audio-mini-realtime-nearSpeech-Language LLM Lite (near-field)Baidu AI Cloud Speech, S2S Baidu AI Cloud Speech S2S – 0/19 ¥16.00 per 1M tokens
audio-realtime-farSpeech-Language LLM Pro (far-field)Baidu AI Cloud Speech, S2S Baidu AI Cloud Speech S2S – 0/19 ¥64.00 per 1M tokens
audio-realtime-nearSpeech-Language LLM Pro (near-field)Baidu AI Cloud Speech, S2S Baidu AI Cloud Speech S2S – 0/19 ¥64.00 per 1M tokens Default
qianfan-realtime-flex-v1Speech-Language LLM FlexBaidu AI Cloud Speech, S2S, beta Baidu AI Cloud Speech S2S – 0/19 – Beta
higgs-realtimeHiggs RealtimeBoson AI, S2S Boson AI S2S – 0/19 $0.75 per 1M tokens Default
gemini-2.5-flash-native-audio-preview-12-2025Gemini 2.5 Flash Native Audio Preview (12-2025)Google Cloud, S2S, ends 2027-03-31 Google Cloud S2S Many 0/19 $3.00 per 1M tokens Ends 2027-03-31
gemini-3.1-flash-live-previewGemini 3.1 Flash Live PreviewGoogle Cloud, S2S, beta Google Cloud S2S Many 0/19 $3.00 per 1M tokens Beta
gemini-3.5-live-translate-previewGemini 3.5 Live Translate PreviewGoogle Cloud, S2S, beta Google Cloud S2S Many 0/19 $3.50 per 1M tokens Beta
gemini-3.8-liveGemini 3.8 LiveGoogle Cloud, S2S Google Cloud S2S Many 0/19 $3.00 per 1M tokens Default
gemini-3.8-live-extended-thinkingGemini 3.8 Live Extended ThinkingGoogle Cloud, S2S Google Cloud S2S Many 0/19 $3.00 per 1M tokens
gemini-live-2.5-flash-native-audioGemini Live 2.5 Flash Native Audio (Vertex AI)Google Cloud, S2S, ends 2026-12-13 Google Cloud S2S Many 0/19 – Ends 2026-12-13
s2s-translateGradium Speech-to-Speech TranslateGradium, S2S Gradium S2S 5 0/19 – Default
fluid-1Kugel Fluid 1KugelAudio, S2S, beta KugelAudio S2S 8 0/19 – Beta
gpt-realtimeGPT-RealtimeOpenAI, S2S, ends 2027-01-20 OpenAI S2S – 0/19 $32.00 per 1M tokens Ends 2027-01-20
gpt-realtime-1.5GPT-Realtime-1.5OpenAI, S2S OpenAI S2S – 0/19 $32.00 per 1M tokens
gpt-realtime-2GPT-Realtime-2OpenAI, S2S OpenAI S2S – 0/19 $32.00 per 1M tokens
gpt-realtime-2.1GPT-Realtime-2.1OpenAI, S2S OpenAI S2S – 0/19 $32.00 per 1M tokens
gpt-realtime-2.1-miniGPT-Realtime-2.1 miniOpenAI, S2S OpenAI S2S – 0/19 $10.00 per 1M tokens
gpt-realtime-2025-08-28GPT-Realtime (2025-08-28)OpenAI, S2S, ends 2027-01-20 OpenAI S2S – 0/19 $32.00 per 1M tokens Ends 2027-01-20
gpt-realtime-miniGPT-Realtime miniOpenAI, S2S, ends 2027-01-20 OpenAI S2S – 0/19 $10.00 per 1M tokens Ends 2027-01-20
gpt-realtime-mini-2025-12-15GPT-Realtime mini (2025-12-15)OpenAI, S2S, ends 2027-01-20 OpenAI S2S – 0/19 $10.00 per 1M tokens Ends 2027-01-20
stepaudio-2.5-realtimeStepAudio 2.5 RealtimeStepFun, S2S StepFun S2S 1 0/19 $1.50 per 1M tokens Default
stepaudio-3-realtime-previewStepAudio 3 Realtime (Preview)StepFun, S2S, beta StepFun S2S 2 0/19 – Beta
1.2.1.1Doubao Realtime Voice O2.0 (Omni)Volcengine, S2S Volcengine S2S 2 0/19 ¥80.00 per 1M tokens
1.2.6.1Doubao Realtime Voice 3.0 (Seeduplex, full-duplex)Volcengine, S2S Volcengine S2S 2 0/19 ¥80.00 per 1M tokens
2.2.0.0Doubao Realtime Voice SC2.0 (Strong Character)Volcengine, S2S Volcengine S2S 2 0/19 ¥80.00 per 1M tokens
volc.service_type.10053Doubao Simultaneous Interpretation 2.0Volcengine, S2S Volcengine S2S 16 0/19 ¥80.00 per 1M tokens
glm-realtime-airGLM-Realtime-AirZhipu AI (Z.ai), S2S Zhipu AI (Z.ai) S2S – 0/19 ¥0.3 per minute
glm-realtime-flashGLM-Realtime-FlashZhipu AI (Z.ai), S2S Zhipu AI (Z.ai) S2S – 0/19 ¥0.18 per minute

Questions

What is the cheapest realtime speech-to-speech API?
The lowest published USD list price is Speech Realtime DeepSeek V4 Flash (Yandex SpeechKit, $0.78 per hour). Next cheapest: Speech Realtime Max TTS Live (Yandex SpeechKit, $0.78 per hour); GPT-Realtime-Translate (OpenAI, $2.04 per hour).
Which providers offer realtime speech-to-speech?
16 providers list 59 models: Alibaba Cloud Model Studio (13), OpenAI (11), Google Cloud (6), Baidu AI Cloud Speech (5), Volcengine (4), Inworld AI (3), Azure Speech (3), Yandex SpeechKit (2), ElevenLabs (2), xAI (2) and 6 more.
Are any realtime speech-to-speech models being shut down?
6 have an announced shutdown date: Gemini Live 2.5 Flash Native Audio (Vertex AI) (Google Cloud) on 2026-12-13, GPT-Realtime (OpenAI) on 2027-01-20, GPT-Realtime (2025-08-28) (OpenAI) on 2027-01-20, GPT-Realtime mini (OpenAI) on 2027-01-20, GPT-Realtime mini (2025-12-15) (OpenAI) on 2027-01-20 and 1 more.
Where does this data come from?
From each provider's own API, documentation and pricing pages, synced and reviewed in git; the latest change on this page was on 2026-11-20. Every price change, new model and shutdown is in the public changelog at /changes.

Speech-to-speech by feature

Speech-to-speech by language

Other model types

Esc

↑↓ move↵ open