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

> Qwen3-TTS 12Hz 1.7B CustomVoice scores 58 (C) to Audio8-TTS-Realistic 0.6B's 51.5 (D) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice
- Markdown: https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice.md (~2,400 tokens)
- Slim: https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice.min.md (~480 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-30

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.

- Audio8-TTS-Realistic 0.6B: grade D, 51.5/100, rank #103 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/audio8-tts-realistic-0-6b.md · JSON https://www.anchorterminal.com/api/v1/tools/audio8-tts-realistic-0-6b.json
- Qwen3-TTS 12Hz 1.7B CustomVoice: grade C, 58/100, rank #73 of 117 open-weight models. Markdown https://www.anchorterminal.com/tools/qwen3-tts-1-7b-customvoice.md · JSON https://www.anchorterminal.com/api/v1/tools/qwen3-tts-1-7b-customvoice.json
- Best text-to-speech APIs for AI agents: https://www.anchorterminal.com/best/text-to-speech/index.md
- All 94 tts comparisons: https://www.anchorterminal.com/compare/text-to-speech/index.md
- Best voice cloning and custom voice APIs for AI agents: https://www.anchorterminal.com/best/voice-cloning/index.md
- All 94 cloning comparisons: https://www.anchorterminal.com/compare/voice-cloning/index.md

## Which one, for what

### Audio8-TTS-Realistic 0.6B (D)

Good 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)

Good 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

| Category | Weight | Audio8-TTS-Realistic 0.6B | Qwen3-TTS 12Hz 1.7B CustomVoice | Edge |
| --- | --- | --- | --- | --- |
| Capability | 35%, pending | pending | pending | not scored in this run |
| Reach | 25% (25 this run) | 55 | 60 | Qwen3-TTS 12Hz 1.7B CustomVoice +5 |
| Risk | 20% (20 this run) | 40 | 45 | Qwen3-TTS 12Hz 1.7B CustomVoice +5 |
| Agent interface | 10% (10 this run) | 60 | 55 | Audio8-TTS-Realistic 0.6B +5 |
| Documentation and upkeep | 10% (10 this run) | 57 | 36 | Audio8-TTS-Realistic 0.6B +21 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **51.5 · D** | **58 · C** | |

## Facts side by side

| Fact | Audio8-TTS-Realistic 0.6B | Qwen3-TTS 12Hz 1.7B CustomVoice |
| --- | --- | --- |
| Kind | Open-weight model | Open-weight model |
| Vendor | Edge0 | Alibaba (Qwen team) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  |  |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | Apache-2.0 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-27 | 2026-01-29 |
| Terms last updated | no document linked | 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 | none | 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.

**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.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice.json, and with the fewest tokens: https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-qwen3-tts-1-7b-customvoice.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "audio8-tts-realistic-0-6b", "b": "qwen3-tts-1-7b-customvoice"}`. From a terminal: `anchor compare audio8-tts-realistic-0-6b qwen3-tts-1-7b-customvoice`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/audio8-tts-realistic-0-6b.json and https://www.anchorterminal.com/api/v1/tools/qwen3-tts-1-7b-customvoice.json

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

- [Audio8-TTS-Realistic 0.6B vs Fish Audio Drama 3](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-fish-audio-drama-3.md)
- [Audio8-TTS-Realistic 0.6B vs Fish Audio S2 Pro](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-fish-audio-s2-pro.md)
- [Audio8-TTS-Realistic 0.6B vs Ming-3.0-tts-0.5B](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-ming-3-0-tts-0-5b.md)
- [Audio8-TTS-Realistic 0.6B vs Ming-3.0-tts-tiny](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-ming-3-0-tts-tiny.md)
- [Audio8-TTS-Realistic 0.6B vs OmniVoice](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-omnivoice.md)
- [Audio8-TTS-Realistic 0.6B vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/audio8-tts-realistic-0-6b-vs-vieneu-tts-v3-turbo.md)
- [Fish Audio Drama 3 vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/fish-audio-drama-3-vs-qwen3-tts-1-7b-customvoice.md)
- [Fish Audio S2 Pro vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/fish-audio-s2-pro-vs-qwen3-tts-1-7b-customvoice.md)
- [Ming-3.0-tts-0.5B vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/ming-3-0-tts-0-5b-vs-qwen3-tts-1-7b-customvoice.md)
- [Ming-3.0-tts-tiny vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/ming-3-0-tts-tiny-vs-qwen3-tts-1-7b-customvoice.md)
- [OmniVoice vs Qwen3-TTS 12Hz 1.7B CustomVoice](https://www.anchorterminal.com/compare/omnivoice-vs-qwen3-tts-1-7b-customvoice.md)
- [Qwen3-TTS 12Hz 1.7B CustomVoice vs VieNeu-TTS v3 Turbo](https://www.anchorterminal.com/compare/qwen3-tts-1-7b-customvoice-vs-vieneu-tts-v3-turbo.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp