Write a review

Head to head · Text-to-speech · October 2026 research run

Fish Audio S2 Pro vs OmniVoice

OmniVoice scores 56.9 (C) on agent readiness against Fish Audio S2 Pro's 52.5 (D), and leads in 2 of 5 scored categories. Fish Audio S2 Pro leads on reach, 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

Fish Audio S2 ProFish Audio · Open-weight model D52.5/100#89 of 107 open-weight models OmniVoicek2-fsa (Next-gen Kaldi) · Open-weight model C56.9/100#75 of 107 open-weight models

Which one, for what

Fish Audio S2 Pro D

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

  • Reach, 50 against 40
  • Agent interface, 70 against 50
  • Documentation and upkeep, 56 against 48

Watch for

Research and non-commercial use only; commercial use, internal business use and hosted services need a separate licence

OmniVoice C

Best for Research and non-commercial agents that need cloning or designed voices in low-resource languages on a small GPU

Ahead on

  • Capability, 86 against 61
  • Risk, 35 against 30

Watch for

Weights are non-commercial by the card, and the bundled tokenizer adds Boson AI's licence with a 100,000-user threshold

Score by category

CategoryWeight this runFish Audio S2 ProOmniVoiceEdge
Capability35%356186OmniVoice +25
Reach25%255040Fish Audio S2 Pro +10
Risk20%203035OmniVoice +5
Agent interface10%107050Fish Audio S2 Pro +20
Documentation and upkeep10%105648Fish Audio S2 Pro +8
Negative events≤1500
TotalD 52.5/100C 56.9/100

Facts side by side

FactFish Audio S2 ProOmniVoice
KindOpen-weight modelOpen-weight model
VendorFish Audiok2-fsa (Next-gen Kaldi)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceFish 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 2026CC-BY-NC (weights, per the card); Apache-2.0 (code)
Read-only variant documentednono
llms.txtnono
Last release2026-03-112026-07-03
Terms last updatedno document linked
Privacy policy last updatedno document linkedno 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 reviews2.3/5 (4)2.3/5 (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.

OmniVoice

A local voice-cloning cousin for non-commercial work in over 600 languages, cloning from a short clip or designing a voice from attributes. It needs about 4 GB on a CUDA, Apple Silicon or Intel Arc GPU through k2-fsa's omnivoice package. The main risk is the licence, changed from Apache 2.0 to non-commercial in July 2026 without a note.

Before you call either

Fish Audio S2 Pro

  1. Install fish-speech from GitHub (uv sync --python 3.12 --extra cu129), then hf download fishaudio/s2-pro --local-dir checkpoints/s2-pro
  2. 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; check GET /v1/health
  3. 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 pass reference_id
  4. Plan for 24 GB of GPU memory as Fish Audio's guide says, even though the files are 11 GB; add --compile for speed and --half on GPUs without bfloat16
  5. 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)
  6. Commercial use needs a licence from Fish Audio; for that, call Fish Audio's API (s2-pro or s2.1-pro) instead

OmniVoice

  1. Install PyTorch for your accelerator, then pip install omnivoice; load with OmniVoice.from_pretrained('k2-fsa/OmniVoice', device_map='cuda:0', dtype=torch.float16) (or mps, or xpu)
  2. Clone with model.generate(text=..., ref_audio='ref.wav', ref_text='...'); omitting ref_text loads a Whisper model to transcribe the clip
  3. Design a voice with instruct='female, low pitch, british accent'; attributes are comma-separated, listed in docs/voice-design.md
  4. Output is a list of numpy arrays at 24 kHz; write with sf.write('out.wav', audio[0], 24000)
  5. Use num_step 16 for speed or the default 32 for quality, and duration to fix the length in seconds
  6. From the shell, omnivoice-infer --model k2-fsa/OmniVoice --text ... --output out.wav; omnivoice-infer-batch spreads work across GPUs
  7. Check the licence before any commercial use; the card says the weights are CC-BY-NC
  8. Only clone a voice you have the right to use

Questions

Which is better for AI agents, Fish Audio S2 Pro or OmniVoice?

OmniVoice scores 56.9 (C) on agent readiness against Fish Audio S2 Pro's 52.5 (D), and leads in 2 of 5 scored categories. Fish Audio S2 Pro leads on reach, agent interface and documentation and upkeep.

Other comparisons with Fish Audio S2 Pro or OmniVoice

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report