Speech models
14 models in the catalog. Prices are the best (lowest) input price per million tokens across providers.
Speech models — best input prices
Speech synthesis models with live per-provider pricing. Rates are collected directly from provider APIs, not manual reports.
| Model | Type | Providers | Input | Output | Last sync | |
|---|---|---|---|---|---|---|
| AT Audio8/Audio8-TTS-Preview-0.6b | Speech | — | 0 | — | — | |
| FE Fal ElevenLabs TTS Multilingual v2 | Speech | — | 0 | — | — | |
| FS Fal Stable Audio 2.5 | Speech | — | 0 | — | — | |
QT
Qwen/Qwen3-TTS
|
Speech | — | 0 | — | — | |
|
QT
Qwen/Qwen3-TTS-VoiceDesign
|
Speech | — | 0 | — | — | |
|
QT
Qwen3 TTS
|
Speech | 32,768 | 0 | — | — | |
XV
XiaomiMiMo/MiMo-V2.5-tts
|
Speech | — | 0 | — | — | |
|
XV
XiaomiMiMo/MiMo-V2.5-tts-voicedesign
|
Speech | — | 0 | — | — | |
IA
inworld-ai/realtime-tts-1.5-max
|
Speech | — | 0 | — | — | |
|
IA
inworld-ai/realtime-tts-1.5-mini
|
Speech | — | 0 | — | — | |
|
IA
inworld-ai/realtime-tts-2
|
Speech | — | 0 | — | — | |
|
MV
mimo-v2.5-tts
|
Speech | — | 0 | — | — | |
|
MV
mimo-v2.5-tts-voiceclone
|
Speech | — | 0 | — | — | |
|
MV
mimo-v2.5-tts-voicedesign
|
Speech | — | 0 | — | — |