Compare AI audio models

No single model covers every task, so the hub ranks each task separately. By popularity the leaders are currently: Speech to text: Gemini 3.5 Transcribe; Speech output: Kokoro-82M; Real-time voice dialog: GPT-Realtime 2.1; Speech translation: Gemini 3.5 Live Translate; Music and sound: Lyria 3.5; Audio analysis: pyannote Community-1. Popularity measures attention and use, not audio quality. A shared quality benchmark across all models of a task is not available yet, so test two or three candidates with your own recordings.

4 speech output models publish open weights, among them Kokoro-82M, Fish Audio S2 Pro and Maya 2 Native. You can run open models yourself without API fees, but you need suitable hardware, and the license decides commercial use. Hosted voices usually charge per character, token or minute.

10 models in the hub take speech in and answer with speech, which voice agents and phone bots need. The most popular are GPT-Realtime 2.1, Eleven v3 Conversational and Gemini 3.8 Live. Response time and turn-taking decide how natural a conversation feels; compare them in your own setup before you build on one model.

22 of 83 audio models list local deployment on their profile, for example pyannote Community-1, Nemotron-3-Diarization and Confucius4-R2T2. Use the "Runs locally" filter in the table for the full list. Check model size and license on each profile.

35 of 83 models have a published price on their profile. Units differ: per minute or hour of audio, per million characters, per million tokens or in credits, so the table shows each price as the provider states it. Examples: Gemini 3.5 Transcribe: $2 per 1M audio tokens ($0.003 per audio minute); Gemini 3.5 Live Translate: $3.50 per 1M audio tokens ($0.0053 per audio minute).

The hub sorts every model into one of six tasks: Speech to text (30), Speech output (23), Real-time voice dialog (10), Speech translation (7), Music and sound (10), Audio analysis (3). Each model has exactly one task, chosen from its documented input and output.