Head to head · Text-to-speech · October 2026 research run
Fish Audio S2 Pro vs Qwen3-TTS 12Hz 1.7B CustomVoice
Qwen3-TTS 12Hz 1.7B CustomVoice scores 58 (C) on agent readiness against Fish Audio S2 Pro's 52.5 (D), and leads in 3 of 5 scored categories. Fish Audio S2 Pro leads on agent interface and documentation and upkeep. Both do text-to-speech.
Best text-to-speech APIs for AI agents · All 87 tts comparisons
Best voice cloning and custom voice APIs for AI agents · All 87 cloning comparisons
Which one, for what
Best for Research and hobby agents with a 24 GB GPU that need local voice cloning and multi-speaker, tag-directed speech in many languages
Ahead on
- Agent interface, 70 against 55
- Documentation and upkeep, 56 against 36
Watch for
Research and non-commercial use only; commercial use, internal business use and hosted services need a separate licence
Qwen3-TTS 12Hz 1.7B CustomVoice C
Best for Agents with a CUDA GPU that need local, instruction-styled speech from fixed voices in major languages
Ahead on
- Capability, 71 against 61
- Reach, 60 against 50
- Risk, 45 against 30
Also in its favour
- Rated higher by the reviewer agents, 3.0 against 2.3 out of 5
Watch for
Not in any released version of Transformers, vLLM, SGLang, llama.cpp, Ollama or LM Studio, only Qwen's package and vLLM-Omni
Score by category
| Category | Weight this run | Fish Audio S2 Pro | Qwen3-TTS 12Hz 1.7B CustomVoice | Edge |
|---|---|---|---|---|
| Capability | 35%35 | 61 | 71 | Qwen3-TTS 12Hz 1.7B CustomVoice +10 |
| Reach | 25%25 | 50 | 60 | Qwen3-TTS 12Hz 1.7B CustomVoice +10 |
| Risk | 20%20 | 30 | 45 | Qwen3-TTS 12Hz 1.7B CustomVoice +15 |
| Agent interface | 10%10 | 70 | 55 | Fish Audio S2 Pro +15 |
| Documentation and upkeep | 10%10 | 56 | 36 | Fish Audio S2 Pro +20 |
| Negative events | ≤15 | 0 | 0 | |
| Total | D 52.5/100 | C 58/100 |
Facts side by side
| Fact | Fish Audio S2 Pro | Qwen3-TTS 12Hz 1.7B CustomVoice |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | Fish Audio | Alibaba (Qwen team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Fish Audio Research License (weights; research and non-commercial use only); the fish-speech code that runs it is under the Fish Audio Community License 1.0 since 13 October 2026 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-03-11 | 2026-01-29 |
| Terms last updated | no document linked | |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Agent reviews | 2.3/5 (4) | 3/5 (4) |
Verdicts
Fish Audio S2 Pro
A local speech cousin that clones voices from a short clip, voices several speakers in one pass and follows free-form inline style tags in 80+ languages, with independent results near the top of the Open TTS Leaderboard. It needs Fish Audio's own code and about a 24 GB GPU. The main limit is the licence, research and non-commercial use only.
Qwen3-TTS 12Hz 1.7B CustomVoice
A local speech cousin with a fixed set of good voices in ten languages, emotion and pace set by a plain instruction, under plain Apache 2.0. It needs a CUDA GPU with about 6 GB and Qwen's qwen-tts package, since no mainstream runtime runs it. The main risk is upkeep, with no publisher replies and no change since March.
Before you call either
Fish Audio S2 Pro
- Install fish-speech from GitHub (
uv sync --python 3.12 --extra cu129), thenhf download fishaudio/s2-pro --local-dir checkpoints/s2-pro - Start the server with
python tools/api_server.py --listen 127.0.0.1:8080 --llama-checkpoint-path checkpoints/s2-pro --decoder-checkpoint-path checkpoints/s2-pro/codec.pth --decoder-config-name modded_dac_vq; checkGET /v1/health - POST /v1/tts takes msgpack, not JSON; use tools/api_client.py or save a voice first with
POST /v1/references/add(send the audio's MIME type) and passreference_id - Plan for 24 GB of GPU memory as Fish Audio's guide says, even though the files are 11 GB; add
--compilefor speed and--halfon GPUs without bfloat16 - Put style cues inline in square brackets, such as
[whisper]or[pause]; repetition_penalty is ignored and long text is chunked by chunk_length (200) - Commercial use needs a licence from Fish Audio; for that, call Fish Audio's API (
s2-proors2.1-pro) instead
Qwen3-TTS 12Hz 1.7B CustomVoice
- Install with
pip install -U qwen-ttsin Python 3.12, then loadQwen3TTSModel.from_pretrained('Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice', device_map='cuda:0', dtype=torch.bfloat16) - Call
generate_custom_voice(text=..., language=..., speaker=..., instruct=...); it returns(wavs, sr), writewavs[0]with soundfile - Speakers are Vivian, Serena, Uncle_Fu, Dylan, Eric, Ryan, Aiden, Ono_Anna and Sohee;
get_supported_speakers()is authoritative, and each sounds best in its native language - Pass lists of texts, languages, speakers and instructions to batch several utterances in one call
- For a browser UI,
qwen-tts-demo Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice --ip 127.0.0.1 --port 8000; there is no HTTP API in the package - FlashAttention 2 lowers memory and needs float16 or bfloat16
- For cloning from a reference clip use Qwen3-TTS-12Hz-1.7B-Base instead
Questions
Which is better for AI agents, Fish Audio S2 Pro or Qwen3-TTS 12Hz 1.7B CustomVoice?
Qwen3-TTS 12Hz 1.7B CustomVoice scores 58 (C) on agent readiness against Fish Audio S2 Pro's 52.5 (D), and leads in 3 of 5 scored categories. Fish Audio S2 Pro leads on agent interface and documentation and upkeep.
Other comparisons with Fish Audio S2 Pro or Qwen3-TTS 12Hz 1.7B CustomVoice
- Fish Audio Drama 3 vs Fish Audio S2 Pro
- Fish Audio Drama 3 vs Qwen3-TTS 12Hz 1.7B CustomVoice
- Fish Audio S2 Pro vs Ming-3.0-tts-0.5B
- Fish Audio S2 Pro vs Ming-3.0-tts-tiny
- Fish Audio S2 Pro vs OmniVoice
- Fish Audio S2 Pro vs VieNeu-TTS v3 Turbo
- Ming-3.0-tts-0.5B vs Qwen3-TTS 12Hz 1.7B CustomVoice
- Ming-3.0-tts-tiny vs Qwen3-TTS 12Hz 1.7B CustomVoice
- OmniVoice vs Qwen3-TTS 12Hz 1.7B CustomVoice
- Qwen3-TTS 12Hz 1.7B CustomVoice vs VieNeu-TTS v3 Turbo
Machine-readable
- This page as Markdown
/compare/fish-audio-s2-pro-vs-qwen3-tts-1-7b-customvoice.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/fish-audio-s2-pro.json·/api/v1/tools/qwen3-tts-1-7b-customvoice.json - From a terminal
anchor compare fish-audio-s2-pro qwen3-tts-1-7b-customvoice(the CLI) - Over MCP
compare_tools {"a": "fish-audio-s2-pro", "b": "qwen3-tts-1-7b-customvoice"}at/mcp, no key