Models listed
103
Published in this category
Worth weighing up
What goes in and out, licence terms, and whether you can host it yourself
How we treat data
Published specs only — we don't estimate numbers a vendor hasn't stated
Audio-text-to-text models are a source-backed task collection in this directory. The current editorial inventory contains 68 mapped model records. Task membership is a discovery signal, not a performance ranking, deployment recommendation, or proof that every checkpoint accepts the same inputs and returns the same outputs.
Start with the model list, then open each record that matches your data, operating constraints, and intended workflow. Check the primary source, documented modalities, license, release information, and implementation notes before using a model in production.
This collection keeps unsupported pricing, availability, and benchmark claims blank. Each page remains outside the public index until an editor approves its content and related model records.
Scan the table below, then open any model for pricing, limits and the full write-up.
| Gemini 3.8 Flash Google | 89.3 | 1.05M | $0.75 | $3.75 | — |
| Muse Spark 1.3 Meta | — | 1.05M | $1.25 | $4.25 | — |
| Gemini 4 Argon Google | — | 1.05M | $2.00 | $10.00 | — |
| Muse Wonder Meta | — | 1.05M | $4.00 | $20.00 | — |
| MiMo V2.6 Flash RL Xiaomi | 66.9 | 1.05M | $0.14 | $0.28 | — |
| MiMo V2.6 Pro RL Xiaomi | 66.9 | 1.05M | $0.435 | $0.87 | — |
| Qwen-Audio-3.1-Realtime-Plus Alibaba | — | 262.14K | — | — | — |
| Qwen3.8 Omni Flash Qwen | 51.7 | 1M | — | — | — |
| Gemini 3.7 Flash Google | 89.2 | 1.05M | $0.75 | $3.75 | — |
| Gemini Flash Latest Google | 89.0 | 1.05M | $1.50 | $9.00 | — |
| Muse Spark 1.2 Meta | — | 1.05M | $1.25 | $4.25 | — |
| Inkling Small Thinkingmachines | 76.8 | 1.05M | $0.50 | $1.20 | — |
| Gemini 3.5 Flash Lite Google | 89.4 | 1.05M | $0.30 | $2.50 | — |
| Gemini 3.6 Flash Google | 89.4 | 1.05M | $1.50 | $7.50 | — |
| Gemini Flash-Lite Latest Google | 89.0 | 1.05M | $0.25 | $1.50 | — |
| Inkling Thinkingmachines | 76.8 | 1.05M | $1.00 | $4.05 | — |
| Muse Spark 1.1 Meta | 82.0 | 1.05M | $1.25 | $4.25 | — |
| Gemini 3.5 Flash Google | 89.0 | 1.05M | $1.50 | $9.00 | — |
| Gemini 3.1 Flash Lite Google | 89.0 | 1.05M | $0.25 | $1.50 | — |
| Nemotron 3 Nano Omni 30B A3B Reasoning NVIDIA | 72.1 | 256K | $0.00 | $0.00 | — |
| MiMo-V2.5 Xiaomi | 80.4 | 1.05M | $0.14 | $0.28 | — |
| Qwen3.6 27B Alibaba | 77.2 | 262.14K | $0.60 | $3.60 | — |
| Qwen3.6 35B-A3B Alibaba | 77.2 | 262.14K | $0.248 | $1.485 | — |
| Gemini Robotics-ER 1.6 Preview Google | 73.8 | 131.07K | $1.00 | $5.00 | — |
| Gemma 4 E2B IT Google | 64.2 | 131.07K | $0.02 | $0.10 | — |
| Gemma 4 E4B IT Google | 64.2 | 131.07K | $0.04 | $0.20 | — |
| MiMo-V2-Omni Xiaomi | 78.5 | 262.14K | $0.14 | $0.28 | — |
| Nemotron VoiceChat NVIDIA | 39.0 | 128K | $0.00 | $0.00 | — |
| Gemini 3.1 Flash Lite Preview Google | 88.6 | 1.05M | $0.25 | $1.50 | — |
| Qwen3.5 122B-A10B Alibaba | 76.9 | 262.14K | $0.40 | $3.20 | — |
| Qwen3.5 27B Alibaba | 76.9 | 262.14K | $0.30 | $2.40 | — |
| Qwen3.5 35B-A3B Alibaba | 76.9 | 262.14K | $0.25 | $2.00 | — |
| Gemini 3.1 Pro Preview Google | 88.5 | 1.05M | $2.00 | $12.00 | — |
| Gemini 3.1 Pro Preview Custom Tools Google | 88.5 | 1.05M | $2.00 | $12.00 | — |
| Qwen3.5 397B-A17B Alibaba | 76.8 | 262.14K | $0.60 | $3.60 | — |
| X-Ai/Grok-4-Fast-Reasoning xAI | — | 2M | — | — | — |
| Gemini 3 Flash Preview Google | 88.2 | 1.05M | $0.50 | $3.00 | — |
| Gemini 3 Pro Preview Google | 88.0 | 1.05M | $2.00 | $12.00 | — |
| mistralai/Voxtral-Small-24B-2507 mistralai | 32.6 | 32.77K | $0.228 | $0.513 | — |
| Voxtral Mini 3B 2507 Mistral AI | — | 32.77K | — | — | — |
| Voxtral Small (latest) Mistral AI | — | 32K | — | — | — |
| Gemini 2.5 Flash Google | 87.2 | 1.05M | $0.30 | $2.50 | — |
| Gemini 2.5 Flash-Lite Google | 87.2 | 1.05M | $0.10 | $0.40 | — |
| Gemini 2.5 Pro Google | 87.2 | 1.05M | $1.25 | $10.00 | — |
| Gemini 2.5 Pro Preview 06-05 Google | — | 1.05M | — | — | — |
| Gemini 2.0 Flash Google | 66.6 | 1.05M | $0.10 | $0.40 | — |
| Gemini 2.0 Flash-Lite Google | 66.6 | 1.05M | $0.075 | $0.30 | — |
| Vision Large Vispark | — | 1M | — | — | — |
| Vision Medium Vispark | — | 1M | — | — | — |
| Vision Small Vispark | — | 1M | — | — | — |
| Gemini 1.5 Pro Google | 63.6 | 2M | $1.25 | $5.00 | 65 t/s |
| ACE-Step/acestep-transcriber ACE-Step | 5.0 | — | — | — | — |
| ai-babai/gigachat-audio-mlx-q8-bf16 ai-babai | 5.0 | — | — | — | — |
| bartowski/mistralai_Voxtral-Mini-3B-2507-GGUF bartowski | 5.0 | — | — | — | — |
| bartowski/mistralai_Voxtral-Small-24B-2507-GGUF bartowski | 5.0 | — | — | — | — |
| cstr/MOSS-Audio-4B-Instruct-GGUF cstr | 5.0 | — | — | — | — |
| DeSTA-ntu/DeSTA2.5-Audio-Llama-3.1-8B DeSTA-ntu | 5.0 | — | — | — | — |
| fixie-ai/ultravox-v0_2 fixie-ai | 5.0 | — | — | — | — |
| fixie-ai/ultravox-v0_3 fixie-ai | 5.0 | — | — | — | — |
| fixie-ai/ultravox-v0_4 fixie-ai | 5.0 | — | — | — | — |
1–60 of 103 models · select a column to sort
About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.