SFAI / SOURCE-BACKED RESEARCH

Audio generation models

Browse models that generate audio. Check whether an endpoint is intended for speech, music or another audio task.

190 current source-qualified profiles · latest catalog observation 2026-09-27

ACE Step Audio Outpaint

ACE Studio · audio

1 current source-qualified record

Async Text to Speech Pro V1.0

async · audio

1 current source-qualified record

Audio Understanding

Unattributed (via fal) · audio

1 current source-qualified record

Bytedance Seed Speech Text to Speech

ByteDance · audio

1 current source-qualified record

Canopy Labs Orpheus Arabic Saudi

Developer not listed · audio

4,000 context tokens · 1 current source-qualified record · 1 community catalog reference

Canopy Labs Orpheus V1 English

Developer not listed · audio

4,000 context tokens · 1 current source-qualified record · 1 community catalog reference

Chatterbox

Resemble AI · audio

1 current source-qualified record

Chatterbox

Resemble AI · audio

1 current source-qualified record

Chatterbox

Resemble AI · audio

1 current source-qualified record

Chatterboxhd

Resemble AI · audio

1 current source-qualified record

Chatterboxhd

Resemble AI · audio

1 current source-qualified record

CSM-1B

Unattributed (via fal) · audio

1 current source-qualified record

Dia

Unattributed (via fal) · audio

1 current source-qualified record

Dia Tts

Unattributed (via fal) · audio

1 current source-qualified record

DiffRhythm: Lyrics to Song

Unattributed (via fal) · audio

1 current source-qualified record

ElevenLabs Multilingual TTS v2

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

Elevenlabs Music

ElevenLabs · audio

1 current source-qualified record

Elevenlabs Music v2

elevenlabs · audio

1 current source-qualified record

Elevenlabs Music v2.5

elevenlabs · audio

1 current source-qualified record

ElevenLabs TTS Multilingual v2

ElevenLabs · audio

1 current source-qualified record

ElevenLabs-Music

Developer not listed · audio

2,000 context tokens · 1 current source-qualified record · 1 community catalog reference

ElevenLabs-v2.5-Turbo

Developer not listed · audio

128,000 context tokens · 1 current source-qualified record · 1 community catalog reference

ElevenLabs-v3

Developer not listed · audio

128,000 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 2.5 Flash Preview TTS

Google · audio

Community reference $0.50 in / $10.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 2.5 Flash TTS

Google · audio

Community reference $0.50 in / $10.00 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 2.5 Pro Preview TTS

Google · audio

Community reference $1.00 in / $20.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 2.5 Pro TTS

Google · audio

Community reference $1.00 in / $20.00 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 3.1 Flash Live Preview

Google · text, audio

Community reference $0.75 in / $4.50 out per 1M tokens · observed 2026-09-27

131,072 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 3.1 Flash Tts

Unattributed (via fal) · audio

1 current source-qualified record

Gemini 3.1 Flash TTS Preview

Google · audio

Community reference $1.00 in / $20.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 3.1 Flash TTS Preview

Google · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 3.5 Live Translate Preview

Google · audio, text

Community reference $3.50 in / $21.00 out per 1M tokens · observed 2026-09-27

16,384 context tokens · 1 current source-qualified record · 1 community catalog reference

Gemini 3.8 Flash Lite TTS

google · audio

1 current source-qualified record

Gemini 3.8 Flash TTS

Google · audio

Community reference $0.50 in / $9.00 out per 1M tokens · observed 2026-09-27

1 current source-qualified record · 1 community catalog reference

Gemini 3.8 Flash TTS

google · audio

1 current source-qualified record

Gemini 3.8 Flash-Lite TTS

Google · audio

Community reference $0.50 in / $6.00 out per 1M tokens · observed 2026-09-27

1 current source-qualified record · 1 community catalog reference

Gemini 3.8 Live

Google · text, audio

Community reference $0.75 in / $4.50 out per 1M tokens · observed 2026-09-27

1 current source-qualified record · 1 community catalog reference

Gemini 3.8 Live Extended Thinking

Google · text, audio

Community reference $0.75 in / $4.50 out per 1M tokens · observed 2026-09-27

1 current source-qualified record · 1 community catalog reference

Google: Lyria 3 Clip Preview

google · text, audio

From $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

1,048,576 context tokens · 1 current source-qualified record

Google: Lyria 3 Pro Preview

google · text, audio

From $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

1,048,576 context tokens · 1 current source-qualified record

GPT Realtime 1.5

OpenAI · text, audio

Community reference $4.00 in / $16.00 out per 1M tokens · observed 2026-09-27

32,000 context tokens · 1 current source-qualified record · 1 community catalog reference

GPT-5.1

OpenAI · text, image, audio

Community reference $1.25 in / $10.00 out per 1M tokens · observed 2026-09-27

400,000 context tokens · 1 current source-qualified record · 1 community catalog reference

GPT-5.1

OpenAI · text, image, audio

Community reference $1.25 in / $10.00 out per 1M tokens · observed 2026-09-27

400,000 context tokens · 1 current source-qualified record · 1 community catalog reference

GPT-5.1 Codex

OpenAI · text, image, audio

Community reference $1.25 in / $10.00 out per 1M tokens · observed 2026-09-27

400,000 context tokens · 1 current source-qualified record · 1 community catalog reference

GPT-5.1 Codex

OpenAI · text, image, audio

Community reference $1.25 in / $10.00 out per 1M tokens · observed 2026-09-27

400,000 context tokens · 1 current source-qualified record · 1 community catalog reference

GPT-Live 1

OpenAI · text, audio

1 current source-qualified record · 1 community catalog reference

GPT-Realtime mini

OpenAI · text, audio

Community reference $0.60 in / $2.40 out per 1M tokens · observed 2026-09-27

1 current source-qualified record · 1 community catalog reference

GPT-Realtime-1.5

OpenAI · text, audio

Community reference $4.00 in / $16.00 out per 1M tokens · observed 2026-09-27

1 current source-qualified record · 1 community catalog reference

gpt-realtime-2

OpenAI · text, audio

Community reference $4.00 in / $24.00 out per 1M tokens · observed 2026-09-27

1 current source-qualified record · 1 community catalog reference

gpt-realtime-2.1

OpenAI · text, audio

Community reference $4.00 in / $24.00 out per 1M tokens · observed 2026-09-27

128,000 context tokens · 1 current source-qualified record · 1 community catalog reference

GPT-Realtime-2.1

OpenAI · text, audio

Community reference $4.00 in / $24.00 out per 1M tokens · observed 2026-09-27

128,000 context tokens · 1 current source-qualified record · 1 community catalog reference

Grok TTS

xAI · audio

1 current source-qualified record · 1 community catalog reference

Grok Voice

xAI · audio

1 current source-qualified record

Grok Voice

xAI · audio

1 current source-qualified record

Grok Voice Think Fast 1.0

xAI · text, audio

1 current source-qualified record · 1 community catalog reference

Grok Voice Think Fast 2.0

xAI · text, audio

1 current source-qualified record · 1 community catalog reference

Grok Voice TTS 1.0

xAI · audio

15,000 context tokens · 1 current source-qualified record · 1 community catalog reference

Kling TTS

Kuaishou · audio

1 current source-qualified record

Kokoro TTS

Kokoro · audio

1 current source-qualified record

Kokoro TTS (Brazilian Portuguese)

Kokoro · audio

1 current source-qualified record

Kokoro TTS (British English)

Kokoro · audio

1 current source-qualified record

Kokoro TTS (French)

Kokoro · audio

1 current source-qualified record

Kokoro TTS (Hindi)

Kokoro · audio

1 current source-qualified record

Kokoro TTS (Italian)

Kokoro · audio

1 current source-qualified record

Kokoro TTS (Japanese)

Kokoro · audio

1 current source-qualified record

Kokoro TTS (Mandarin Chinese)

Kokoro · audio

1 current source-qualified record

Kokoro TTS (Spanish)

Kokoro · audio

1 current source-qualified record

Lyria

Google · audio

1 current source-qualified record · 1 community catalog reference

Lyria 3 Clip Preview

Developer not listed · text, audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

1,048,576 context tokens · 1 current source-qualified record · 1 community catalog reference

Lyria 3 Clip Preview

Google · text, audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

1,048,576 context tokens · 1 current source-qualified record · 1 community catalog reference

Lyria 3 Pro Preview

Developer not listed · text, audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

1,048,576 context tokens · 1 current source-qualified record · 1 community catalog reference

Lyria 3 Pro Preview

Google · text, audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

1,048,576 context tokens · 1 current source-qualified record · 1 community catalog reference

Lyria 3.5

google · audio

1 current source-qualified record

Lyria2

Google · audio

1 current source-qualified record

magpie-tts-zeroshot

NVIDIA · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

1 current source-qualified record · 1 community catalog reference

Maya

Unattributed (via fal) · audio

1 current source-qualified record

Maya

Unattributed (via fal) · audio

1 current source-qualified record

Maya1

Unattributed (via fal) · audio

1 current source-qualified record

MiMo-V2-TTS

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2-TTS

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2-TTS

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS-VoiceClone

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS-VoiceClone

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS-VoiceClone

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS-VoiceDesign

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS-VoiceDesign

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

MiMo-V2.5-TTS-VoiceDesign

Developer not listed · audio

Community reference $0.00 in / $0.00 out per 1M tokens · observed 2026-09-27

8,192 context tokens · 1 current source-qualified record · 1 community catalog reference

Minimax

MiniMax · audio

1 current source-qualified record

Minimax

MiniMax · audio

1 current source-qualified record

MiniMax (Hailuo AI) Music

MiniMax · audio

1 current source-qualified record

MiniMax (Hailuo AI) Music v1.5

MiniMax · audio

1 current source-qualified record

Minimax Music

MiniMax · audio

1 current source-qualified record

Minimax Music 2.5

MiniMax · audio

1 current source-qualified record

Minimax Music 2.6

MiniMax · audio

1 current source-qualified record

MiniMax Music 3

minimax · audio

1 current source-qualified record

MiniMax Speech 2.6 [HD]

MiniMax · audio

1 current source-qualified record

MiniMax Speech 2.6 [Turbo]

MiniMax · audio

1 current source-qualified record

MiniMax Speech 2.8 [HD]

MiniMax · audio

1 current source-qualified record

MiniMax Speech 2.8 [Turbo]

MiniMax · audio

1 current source-qualified record

MiniMax Speech-02 HD

MiniMax · audio

1 current source-qualified record

MiniMax Speech-02 Turbo

MiniMax · audio

1 current source-qualified record

MiniMax Voice Cloning

MiniMax · audio

1 current source-qualified record

MiniMax Voice Design

MiniMax · audio

1 current source-qualified record

Mirelo SFX

Mirelo AI · audio

1 current source-qualified record

Mirelo SFX V1.5

Mirelo AI · audio

1 current source-qualified record

Mirelo SFX1.6

Mirelo AI · audio

1 current source-qualified record

MMAudio V2 Text to Audio

MMAudio · audio

1 current source-qualified record

music generator

CassetteAI · audio

1 current source-qualified record

OpenAI: GPT Audio

OpenAI · text, audio

Community reference $2.50 in / $10.00 out per 1M tokens · observed 2026-09-27

128,000 context tokens · 1 current source-qualified record · 1 community catalog reference

OpenAI: GPT Audio

openai · text, audio

From $2.50 in / $10.00 out per 1M tokens · observed 2026-09-27

128,000 context tokens · 1 current source-qualified record

OpenAI: GPT Audio Mini

OpenAI · text, audio

Community reference $0.60 in / $2.40 out per 1M tokens · observed 2026-09-27

128,000 context tokens · 1 current source-qualified record · 1 community catalog reference

OpenAI: GPT Audio Mini

openai · text, audio

From $0.60 in / $2.40 out per 1M tokens · observed 2026-09-27

128,000 context tokens · 1 current source-qualified record

Orpheus TTS

Unattributed (via fal) · audio

1 current source-qualified record

Personaplex

Unattributed (via fal) · audio

1 current source-qualified record

Personaplex

Unattributed (via fal) · audio

1 current source-qualified record

Qwen 3 TTS - Clone Voice [0.6B]

Alibaba · audio

1 current source-qualified record

Qwen 3 TTS - Clone Voice [1.7B]

Alibaba · audio

1 current source-qualified record

Qwen 3 TTS - Text to Speech [0.6B]

Alibaba · audio

1 current source-qualified record

Qwen 3 TTS - Text to Speech [1.7B]

Alibaba · audio

1 current source-qualified record

Qwen 3 TTS - Voice Design [1.7B]

Alibaba · audio

1 current source-qualified record

Qwen Audio 3.0 TTS (Flash)

alibaba · audio

1 current source-qualified record

Qwen Omni Turbo (Alibaba Cloud)

Alibaba · text, audio

Community reference $0.20 in / $0.80 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen-Omni Turbo

Alibaba · text, audio

Community reference $0.058 in / $0.23 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen-Omni Turbo

Alibaba · text, audio

Community reference $0.07 in / $0.27 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen-Omni Turbo

Alibaba · text, audio

Community reference $0.20 in / $0.80 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen-Omni Turbo Realtime

Alibaba · text, audio

Community reference $0.23 in / $0.918 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen-Omni Turbo Realtime

Alibaba · text, audio

Community reference $0.27 in / $1.07 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen2.5-Omni 7B

Alibaba · text, audio

Community reference $0.087 in / $0.345 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen2.5-Omni 7B

Alibaba · text, audio

Community reference $0.10 in / $0.40 out per 1M tokens · observed 2026-09-27

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen3 Omni 30B A3B Instruct

Alibaba · text, audio

Community reference $0.25 in / $0.97 out per 1M tokens · observed 2026-09-27

65,536 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen3 TTS VoiceDesign

Alibaba · audio

32,768 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen3-LiveTranslate Flash Realtime

Alibaba · text, audio

Community reference $10.00 in / $10.00 out per 1M tokens · observed 2026-09-27

53,248 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen3-Omni Flash

Alibaba · text, audio

Community reference $0.058 in / $0.23 out per 1M tokens · observed 2026-09-27

65,536 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen3-Omni Flash

Alibaba · text, audio

Community reference $0.43 in / $1.66 out per 1M tokens · observed 2026-09-27

65,536 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen3-Omni Flash Realtime

Alibaba · text, audio

Community reference $0.23 in / $0.918 out per 1M tokens · observed 2026-09-27

65,536 context tokens · 1 current source-qualified record · 1 community catalog reference

Qwen3-Omni Flash Realtime

Alibaba · text, audio

Community reference $0.52 in / $1.99 out per 1M tokens · observed 2026-09-27

65,536 context tokens · 1 current source-qualified record · 1 community catalog reference

S1

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

S2 Pro

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

S2.1 Pro

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

Sam Audio

Unattributed (via fal) · audio

1 current source-qualified record

Sam Audio

Unattributed (via fal) · audio

1 current source-qualified record

Sam Audio

Unattributed (via fal) · audio

1 current source-qualified record

Seed Audio 1.0

ByteDance · audio

1 current source-qualified record

Sonilo V1.1 Text to Music

sonilo · audio

1 current source-qualified record

Sound Effects Generator

CassetteAI · audio

1 current source-qualified record

Stable Audio 2.5

Stability AI · audio

1 current source-qualified record

Stable Audio 2.5

Stability AI · audio

1 current source-qualified record

Stable Audio 2.5 (Text-to-Audio)

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

Stable Audio 25

Stability AI · audio

1 current source-qualified record

Stable Audio 3

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Medium Audio Inpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Medium Audio Outpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Medium Audio to Audio

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Medium Base Audio Inpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Medium Base Audio Outpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Medium Base Audio to Audio

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Medium Base Text to Audio

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small Music Audio Inpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small Music Audio Outpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small Music Base Audio Inpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small Music Base Audio Outpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small Music Base Audio to Audio

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small Music Text to Audio

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small SFX Audio Inpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small SFX Audio Outpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small SFX Base Audio Inpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small SFX Base Audio Outpainting

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small SFX Base Audio to Audio

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small SFX Base Text to Audio

Unattributed (via fal) · audio

1 current source-qualified record

Stable Audio 3 Small SFX Text to Audio

Unattributed (via fal) · audio

1 current source-qualified record

Step TTS 2

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

Step TTS 2

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

StepAudio 2.5 TTS

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

StepAudio 2.5 TTS

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

Tada

Unattributed (via fal) · audio

1 current source-qualified record

Tada TTS 1B

Unattributed (via fal) · audio

1 current source-qualified record

TTS-1

OpenAI · audio

1 current source-qualified record · 1 community catalog reference

TTS-1 HD

OpenAI · audio

1 current source-qualified record · 1 community catalog reference

V1.1

sonilo · audio

1 current source-qualified record

V1.1 Text to Sound Effects

sonilo · audio

1 current source-qualified record

V1.1 Video to Sound Effects

sonilo · audio

1 current source-qualified record

Voxtral Mini TTS (latest)

Developer not listed · audio

1 current source-qualified record · 1 community catalog reference

Zonos-Audio-Clone

Unattributed (via fal) · audio

1 current source-qualified record

Zonos2 Text to Speech

Unattributed (via fal) · audio

1 current source-qualified record

Capabilities are source-reported and do not constitute an independent quality assessment.