Sign in

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

Audio8-TTS-Realistic 0.6B vs Qwen3-TTS 12Hz 1.7B CustomVoice

Qwen3-TTS 12Hz 1.7B CustomVoice scores 58 (C) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 2 of 4 scored categories. Audio8-TTS-Realistic 0.6B leads on agent interface and documentation and upkeep. 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 Qwen3-TTS 12Hz 1.7B CustomVoiceAlibaba (Qwen team) · Open-weight model C58/100#73 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

  • Agent interface, 60 against 55
  • Documentation and upkeep, 57 against 36

Watch for

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

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

  • Reach, 60 against 55
  • Risk, 45 against 40

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

CategoryWeight this runAudio8-TTS-Realistic 0.6BQwen3-TTS 12Hz 1.7B CustomVoiceEdge
Capability35%pendingpendingpendingnot scored in this run
Reach25%255560Qwen3-TTS 12Hz 1.7B CustomVoice +5
Risk20%204045Qwen3-TTS 12Hz 1.7B CustomVoice +5
Agent interface10%106055Audio8-TTS-Realistic 0.6B +5
Documentation and upkeep10%105736Audio8-TTS-Realistic 0.6B +21
Negative events≤1500
TotalD 51.5/100C 58/100

Facts side by side

FactAudio8-TTS-Realistic 0.6BQwen3-TTS 12Hz 1.7B CustomVoice
KindOpen-weight modelOpen-weight model
VendorEdge0Alibaba (Qwen team)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneNone
PricingFreeFree
x402nono
LicenceApache-2.0Apache-2.0
Read-only variant documentednono
llms.txtnono
Last release2026-10-272026-01-29
Terms last updatedno document linkedno 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 reviewsnone3/5 (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.

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

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

Qwen3-TTS 12Hz 1.7B CustomVoice

  1. Install with pip install -U qwen-tts in Python 3.12, then load Qwen3TTSModel.from_pretrained('Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice', device_map='cuda:0', dtype=torch.bfloat16)
  2. Call generate_custom_voice(text=..., language=..., speaker=..., instruct=...); it returns (wavs, sr), write wavs[0] with soundfile
  3. 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
  4. Pass lists of texts, languages, speakers and instructions to batch several utterances in one call
  5. 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
  6. FlashAttention 2 lowers memory and needs float16 or bfloat16
  7. For cloning from a reference clip use Qwen3-TTS-12Hz-1.7B-Base instead

Questions

Which is better for AI agents, Audio8-TTS-Realistic 0.6B or Qwen3-TTS 12Hz 1.7B CustomVoice?

Qwen3-TTS 12Hz 1.7B CustomVoice scores 58 (C) on agent readiness against Audio8-TTS-Realistic 0.6B's 51.5 (D), and leads in 2 of 4 scored categories. Audio8-TTS-Realistic 0.6B leads on agent interface and documentation and upkeep.

Other comparisons with Audio8-TTS-Realistic 0.6B or Qwen3-TTS 12Hz 1.7B CustomVoice

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