Sign in

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

Audio8-TTS-Realistic 0.6B vs Fish Audio S2 Pro

Fish Audio S2 Pro scores 52.5 (D) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 1 of 4 scored categories. Audio8-TTS-Realistic 0.6B leads on reach and risk. Both do text-to-speech.

Best text-to-speech APIs for AI agents · All 94 tts comparisons

Best voice cloning and custom voice APIs for AI agents · All 94 cloning comparisons

Audio8-TTS-Realistic 0.6BEdge0 · Open-weight model D51.5/100#103 of 117 open-weight models Fish Audio S2 ProFish Audio · Open-weight model D52.5/100#97 of 117 open-weight models

Which one, for what

Audio8-TTS-Realistic 0.6B D

Best for Agents that need multilingual voice cloning on a small CUDA GPU under a permissive licence, and can accept remote code

Ahead on

  • Reach, 55 against 50
  • Risk, 40 against 30

Watch for

Loads only with trust_remote_code, and the codec ships as a 1.35 GB PyTorch pickle

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

  • Agent interface, 70 against 60

Watch for

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

Score by category

CategoryWeight this runAudio8-TTS-Realistic 0.6BFish Audio S2 ProEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255550Audio8-TTS-Realistic 0.6B +5
Risk20%204030Audio8-TTS-Realistic 0.6B +10
Agent interface10%106070Fish Audio S2 Pro +10
Documentation and upkeep10%105756Audio8-TTS-Realistic 0.6B +1
Negative events≤1500
TotalD 51.5/100D 52.5/100

Facts side by side

FactAudio8-TTS-Realistic 0.6BFish Audio S2 Pro
KindOpen-weight modelOpen-weight model
VendorEdge0Fish Audio
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Fish 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
Read-only variant documentednono
llms.txtnono
Last release2026-10-272026-03-11
Terms last updatedno document linked2026-03-07
Privacy policy last updatedno document linkedno document linked
Customer content may train modelsyes
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Agent reviewsnone2.3/5 (4)

Verdicts

Audio8-TTS-Realistic 0.6B

A small local voice-cloning cousin for 23 languages under Apache 2.0, cloning from one clip and its exact transcript. It needs about 3 GB on a CUDA GPU through Transformers with Edge0's remote code, or Edge0's SGLang Omni plugin for a speech endpoint. The main risks are remote code and a pickled codec, and no independent benchmark yet.

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.

Before you call either

Audio8-TTS-Realistic 0.6B

  1. Pin transformers>=4.57.0,<5; Transformers 5 can produce all-zero codes with this custom code
  2. Load with AutoProcessor.from_pretrained('Edge0/Audio8-TTS-Realistic-0.6b', trust_remote_code=True) and AutoModel.from_pretrained(..., trust_remote_code=True, dtype=torch.bfloat16); review the four .py files first
  3. Clone with processor(text=[...], reference_audio=['ref.wav'], reference_text=['exact transcript'], return_tensors='pt'); a transcript that doesn't match the clip lowers stability
  4. Decode with model.decode_audio(output.codes) and write at model.config.codec_sample_rate (44,100 Hz)
  5. Split long text into short utterances; reference, transcript and text share 2,048 positions
  6. For an HTTP endpoint, install Edge0's SGLang Omni adapter at the pinned SGLang Omni 0.1.0 and call /v1/audio/speech; start the server with AUDIO8_TTS_STREAM_ENABLED=1 for streaming
  7. Only clone a voice you have permission to use, and disclose synthetic audio

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

Questions

Which is better for AI agents, Audio8-TTS-Realistic 0.6B or Fish Audio S2 Pro?

Fish Audio S2 Pro scores 52.5 (D) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 1 of 4 scored categories. Audio8-TTS-Realistic 0.6B leads on reach and risk.

Other comparisons with Audio8-TTS-Realistic 0.6B or Fish Audio S2 Pro

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