Speech-to-text, TTS, and audio analysis
63
Models
12
Benchmarks
34
Providers
59
Open Weight
61
Deployable Now
59 self-host
63
Structured benchmark-backed rows
0
Signal-backed rows without full normalized tables
0
Benchmark-expected rows still catching up
| # | Model | Economic Footprint | Quality | Params | Open ASR Mean WER | SWE-Bench | GAIA | Aider Polyglot | $/M In | Speed | Open |
|---|---|---|---|---|---|---|---|---|---|---|---|
2 | whisper-large-v3-turbo OpenAI Open Weights |
| 38.2 |
| 54.0 |
| 809M |
| 92.2 |
| — |
| — |
| — |
Free Free |
| — |
1 | whisper-large-v3 OpenAI Open WeightsStructured | 38.2 | 53.2 | 2B | 92.6 | — | — | — | Free Free | — |
48 | TTS-1 HD OpenAI Structured | 37.2 | 13.3 | Undisclosed | — | 42.4 | — | — | $30.00/M Cheapest verified | — |
16 | whisper-tiny.en OpenAI Open WeightsStructured | 36.9 | 45.2 | 38M | 87.2 | — | — | — | Free Free | — |
17 | whisper-small.en OpenAI Open WeightsStructured | 36.5 | 45.1 | 242M | 91.4 | — | — | — | Free Free | — |
5 | qwen3-tts Qwen Open WeightsStructured | 35.7 | 45.3 | Unknown | — | 69.6 | 44.2 | — | Free Free | — |
6 | GPT Audio OpenAI SubscriptionStructured | 34.8 | 17.1 | Undisclosed | — | 42.4 | — | — | $2.50/M Cheapest verified | — |
36 | stt_en_conformer_ctc_large NVIDIA Open WeightsStructured | 32.7 | 43.2 | Unknown | 91.7 | — | — | — | Free Free | — |
13 | Qwen3-ASR-1.7B Qwen Open WeightsStructured | 32.5 | 51.5 | 2B | 94.2 | 69.6 | 44.2 | 8.0 | Free Free | — |
21 | Qwen3-ASR-0.6B Qwen Open WeightsStructured | 30.7 | 53.6 | 938M | 93.6 | — | 44.2 | — | Free Free | — |
19 | Qwen3-TTS-12Hz-1.7B-CustomVoice Qwen Open WeightsStructured | 30.6 | 49.0 | 2B | — | 69.6 | 44.2 | 8.0 | Free Free | — |
11 | VibeVoice-ASR Microsoft Open WeightsStructured | 30.2 | 57.0 | 9B | 92.2 | — | — | — | Free Free | — |
33 | Phi-4-multimodal-instruct Microsoft Open WeightsStructured | 28.5 | 38.8 | 6B | — | — | — | — | Free Free | — |
18 | cohere-transcribe-03-2026 Cohere Open WeightsStructured | 28.3 | 52.8 | 2B | 94.6 | 42.4 | — | — | Free Free | — |
22 | GPT-4o Transcribe Diarize OpenAI SubscriptionStructured | 27.0 | 19.2 | Undisclosed | — | — | 60.6 | — | $2.50/M Cheapest verified | — |
39 | Qwen3-TTS-12Hz-0.6B-CustomVoice Qwen Open WeightsStructured | 26.5 | 43.8 | 906M | — | — | 44.2 | — | Free Free | — |
38 | Qwen3-TTS-12Hz-0.6B-Base Qwen Open WeightsStructured | 26.3 | 43.8 | 915M | — | — | 44.2 | — | Free Free | — |
40 | Qwen3-TTS-12Hz-1.7B-VoiceDesign Qwen Open WeightsStructured | 26.1 | 43.7 | 2B | — | — | 44.2 | — | Free Free | — |
42 | Qwen3-ForcedAligner-0.6B Qwen Open WeightsStructured | 26.0 | 43.1 | 918M | — | — | 44.2 | — | Free Free | — |
51 | canary-qwen-2.5b NVIDIA Open WeightsStructured | 25.6 | 35.8 | 3B | — | 40.2 | 4.7 | — | Free Free | — |
26 | GLM ASR 2512 Z.ai Structured | 24.3 | 38.6 | Undisclosed | — | 73.8 | — | — | — | — |
30 | Qwen3-ASR-1.7B-hf Qwen Open WeightsStructured | 24.0 | 46.2 | 2B | — | — | 44.2 | — | Free Free | — |
37 | Qwen3-ASR-0.6B-hf Qwen Open WeightsStructured | 23.6 | 44.9 | 782M | — | — | 44.2 | — | Free Free | — |
50 | Voxtral-4B-TTS-2603 Mistral AI Open WeightsStructured | 21.0 | 38.8 | 4B | — | 42.4 | — | — | Free Free | — |
25 | vstr Alignment-Lab-AI Open WeightsStructured | — | — | 442M | — | 56.4 | — | — | Free Free | — |
26 | qwen3-asr-0.6b-GGUF cstr Open WeightsStructured | — | — | 600M | — | — | 44.2 | — | Free Free | — |
27 | qwen3-asr-1.7b-GGUF cstr Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
28 | qwen3-TTS-KSA vadimbelsky Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
29 | Qwen3-ASR-1.7B-nvfp4 vrfai Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
30 | Qwen3-ASR-1.7B-JA neosophie Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
31 | Qwen3-TTS-GGUF Serveurperso Open WeightsStructured | — | — | Unknown | — | — | 44.2 | — | Free Free | — |
32 | qwen3-tts-0.6b-base-GGUF cstr Open WeightsStructured | — | — | 600M | — | — | 44.2 | — | Free Free | — |
33 | qwen3-tts-1.7b-base-GGUF cstr Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
34 | Qwen3-ASR-0.6B-int8-QAD vrfai Open WeightsStructured | — | — | 600M | — | — | 44.2 | — | Free Free | — |
35 | whisper-large-v3-turbo deepdml Open WeightsStructured | — | — | 809M | 92.2 | — | — | — | Free Free | — |
36 | qwen3-tts-emotion-tags SpragAI Open WeightsStructured | — | — | Unknown | — | — | 44.2 | — | Free Free | — |
37 | qwen3-asr-0.6b-onnx andrewleech Open WeightsStructured | — | — | 600M | — | — | 44.2 | — | Free Free | — |
38 | qwen3-asr-1.7b-onnx andrewleech Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
39 | Qwen3-ASR-1.7B-hf-beam4 bosonai Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
40 | qwen3-tts-coreml FluidInference Open WeightsStructured | — | — | Unknown | — | — | 44.2 | — | Free Free | — |
41 | Qwen3-ASR-0.6B-Albanian Kushtrim Open WeightsStructured | — | — | 782M | — | — | 44.2 | — | Free Free | — |
42 | whisper-large-v3-turbo metythorn Open WeightsStructured | — | — | 809M | 92.2 | — | — | — | Free Free | — |
43 | Qwen3-ASR-1.7B-MLX-4bit aufklarer Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
44 | granite-4.0-1b-speech ibm-granite Open WeightsStructured | — | — | 2B | — | 42.4 | — | — | Free Free | — |
45 | Qwen3-ASR-Enhanced-v0.1 mrfakename Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
46 | Qwen3-ASR-1.7B-Lyrics-Viet sunbv56 Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
47 | qwen3-tts-0.6b-indonesian wt5719001 Open WeightsStructured | — | — | 906M | — | — | 44.2 | — | Free Free | — |
48 | qwen3-tts-1.7b-voicedesign-GGUF cstr Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
49 | qwen3-tts-0-6b-base-mix-precision Arm Open WeightsStructured | — | — | 6B | — | — | 44.2 | — | Free Free | — |
50 | Qwen3-tts-0.6b-gguf-for-koboldcpp Jahaz Open WeightsStructured | — | — | 600M | — | — | 44.2 | — | Free Free | — |
51 | Qwen3-ASR-0.6B-Backpack-ASR backpack-run Open WeightsStructured | — | — | 938M | — | — | 44.2 | — | Free Free | — |
52 | qwen3-edgellm-jetson-artifacts harvestsu Open WeightsStructured | — | — | Unknown | — | — | 44.2 | — | Free Free | — |
53 | Qwen3-TTS-12Hz-0.6B-Base-bf16 mlx-community Open WeightsStructured | — | — | 600M | — | — | 44.2 | — | Free Free | — |
54 | Qwen3-TTS-12Hz-1.7B-Base-8bit mlx-community Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
55 | qwen3-tts-0-6b-custom-voice-mix-precision Arm Open WeightsStructured | — | — | 6B | — | — | 44.2 | — | Free Free | — |
56 | Qwen3-ASR-1.7B_Jordanian_Dialect_Arabic sarapd Open WeightsStructured | — | — | 7B | — | — | 44.2 | — | Free Free | — |
57 | whisper-large-v3-turbo-bulgarian-bulgaria sam8000 Open WeightsStructured | — | — | 809M | — | — | — | — | Free Free | — |
58 | Qwen3-TTS-12Hz-1.7B-CustomVoice-8bit mlx-community Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
59 | Qwen3-TTS-12Hz-1.7B-CustomVoice-bf16 mlx-community Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
60 | Qwen3-TTS-12Hz-1.7B-VoiceDesign-8bit mlx-community Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
61 | Qwen3-TTS-12Hz-1.7B-VoiceDesign-bf16 mlx-community Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
62 | NOESIS-Qwen3-TTS-1.7B-Talker-Combo-LLM2-ASR2-BF16 AMAImedia Open WeightsStructured | — | — | 2B | — | — | 44.2 | — | Free Free | — |
63 | whisper-large-v3 ivrit-ai Open WeightsStructured | — | — | 2B | 92.6 | — | — | — | Free Free | — |